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

    Neuronpedia

    INDEX
    Explanations

    expressions of human moral complexity and ethical dilemmas

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

    many multitude many of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     HttpNotFound
    -0.33
    kwds
    -0.32
     <>",
    -0.32
    zeczytaj
    -0.31
    angani
    -0.30
    Hochspringen
    -0.29
     bese
    -0.29
     Vergnügen
    -0.29
    tableLayoutPanel
    -0.28
    GMENT
    -0.28
    POSITIVE LOGITS
    fjspx
    0.58
    Portail
    0.57
    новништво
    0.55
    ########.
    0.55
    SourceChecksum
    0.54
    Datuak
    0.52
    TagMode
    0.52
    forRoot
    0.49
    OGND
    0.47
     ProtoMessage
    0.47
    Act Density 0.019%

    No Known Activations