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

    Neuronpedia

    INDEX
    Explanations

    conditional and troubleshooting phrases related to software usage

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

    your or maybe not working

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AntiForgeryToken
    -0.54
    PhysRevD
    -0.54
     surla
    -0.52
    béco
    -0.51
     invokingState
    -0.50
    __':
    -0.49
    recated
    -0.49
    __':
    -0.47
    Izvori
    -0.46
    SharedCtor
    -0.45
    POSITIVE LOGITS
     ваших
    0.36
    tonode
    0.36
     spot
    0.35
     visibility
    0.35
     incorrect
    0.34
     vaš
    0.34
     Maybe
    0.34
    yourself
    0.33
    your
    0.33
     vostro
    0.32
    Act Density 0.025%

    No Known Activations