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

    Neuronpedia

    INDEX
    Explanations

    underscore characters and numeric tokens

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

    Kennedy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AccessorTable
    -0.63
    /*
    -0.56
     cref
    -0.52
    发表于
    -0.48
    новништво
    -0.48
    yarnpkg
    -0.47
    Архівовано
    -0.47
     <<<<<<<<<<<<<<
    -0.46
    httphttps
    -0.46
    GEBURTSDATUM
    -0.46
    POSITIVE LOGITS
     contextLoads
    0.50
     Kennedy
    0.47
     KENN
    0.45
    ̈́
    0.41
    protoimpl
    0.41
    AutoScaleMode
    0.40
     PAN
    0.40
    qed
    0.40
    zane
    0.40
     Generation
    0.38
    Act Density 0.011%

    No Known Activations