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

    Neuronpedia

    INDEX
    Explanations

    numerical values, particularly the number 9

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

    numbers in calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.70
    zzleHttp
    -0.59
    mobileqq
    -0.52
    argout
    -0.51
    onedDateTime
    -0.51
    quelize
    -0.50
    principalColumn
    -0.50
    WillAppear
    -0.49
     rospy
    -0.49
     typelib
    -0.48
    POSITIVE LOGITS
    trex
    0.47
    eche
    0.46
    weis
    0.46
    thal
    0.45
    ests
    0.43
    blad
    0.43
    oma
    0.42
    inburgh
    0.42
    undu
    0.41
    oche
    0.41
    Act Density 0.061%

    No Known Activations