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

    Neuronpedia

    INDEX
    Explanations

    boolean values indicating success or failure outcomes

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

    user input start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ::<
    -0.43
    arten
    -0.42
    lebo
    -0.42
    orno
    -0.41
    junction
    -0.41
     wizy
    -0.40
     junction
    -0.40
    oflu
    -0.40
    quec
    -0.40
     ArrayAdapter
    -0.39
    POSITIVE LOGITS
     AssemblyTitle
    0.53
    verwijspagina
    0.52
    Aholisi
    0.50
     ब्रेकडाउन
    0.49
     متعلقه
    0.49
     فريبيس
    0.48
    RTGC
    0.47
    ngdoc
    0.47
    PositiveButton
    0.46
    endpush
    0.45
    Act Density 0.005%

    No Known Activations