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

    Neuronpedia

    INDEX
    Explanations

    expressions related to visual imagery and comparisons

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

    like a comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.61
    adaptiveStyles
    -0.53
     ब्रेकडाउन
    -0.53
    NewUrlParser
    -0.51
    сылкі
    -0.51
    MemoryWarning
    -0.51
    -------------</
    -0.51
     begründet
    -0.50
     متعلقه
    -0.50
     TextInputType
    -0.49
    POSITIVE LOGITS
    ToScroll
    0.36
     scientific
    0.35
     Scientific
    0.35
    綢
    0.34
     Sk
    0.33
     precisely
    0.33
     sk
    0.33
     science
    0.33
    TagHelper
    0.32
     recon
    0.32
    Act Density 0.030%

    No Known Activations