Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals, particularly Ralph, in the context of their contributions or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code-related tokens and names, like "Ralph"

    np_acts-logits-general · gemini-2.0-flash

    Ralph followed by Rap

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    intios
    -0.55
    AsUp
    -0.45
    endregion
    -0.44
    麿
    -0.42
    VersionUID
    -0.40
    Према
    -0.39
    RTLI
    -0.39
    InputTagHelper
    -0.38
    磐
    -0.38
    DockStyle
    -0.38
    POSITIVE LOGITS
     nothwendig
    0.51
     dieß
    0.49
     dezelve
    0.48
     fubject
    0.47
     abſ
    0.47
     teuer
    0.47
     étoient
    0.46
    httphttps
    0.46
     sogget
    0.46
     ſei
    0.45
    Act Density 0.014%

    No Known Activations