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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to legal and contractual obligations

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

    describes actions and consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.72
    featureID
    -0.68
    principalTable
    -0.64
     ivelany
    -0.63
    ьаж
    -0.61
     bcrypt
    -0.60
     мәкал
    -0.60
     handleMessage
    -0.59
     ब्रेकडाउन
    -0.58
    ⦊
    -0.56
    POSITIVE LOGITS
     Región
    0.37
     Colección
    0.37
     Constitución
    0.34
    Royaume
    0.34
     Verband
    0.34
     Tief
    0.33
     bisschen
    0.33
     infecciones
    0.32
     herzlich
    0.31
     okuyayım
    0.31
    Act Density 0.995%

    No Known Activations