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

    Neuronpedia

    INDEX
    Explanations

    themes related to morality and human duality

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

    human beings and individuals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AfterClass
    -0.35
    soon
    -0.34
     unknownFields
    -0.34
     Ride
    -0.34
    ạch
    -0.33
     pending
    -0.33
     υ
    -0.32
    衛門
    -0.32
    ef
    -0.31
    Subviews
    -0.31
    POSITIVE LOGITS
    windowFixed
    0.55
     ſind
    0.53
     становника
    0.51
    AddTagHelper
    0.50
     dieſes
    0.49
     humans
    0.48
    StoryboardSegue
    0.48
     Italijanski
    0.47
    ########.
    0.47
     OMITBAD
    0.47
    Act Density 0.087%

    No Known Activations