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

    Neuronpedia

    INDEX
    Explanations

    complex relationships and commitments within narratives

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

    feature smoothing load curves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.60
    principalColumn
    -0.54
     ModelExpression
    -0.52
    "=>$
    -0.50
    ]")]
    -0.50
    assemblée
    -0.49
    脚注の使い方
    -0.48
     vostri
    -0.48
    :✨
    -0.46
    TheReal
    -0.46
    POSITIVE LOGITS
     beginnetje
    0.46
    Становништво
    0.45
    AnchorStyles
    0.45
     Pingback
    0.41
    DebuggerNonUser
    0.38
    رشف
    0.37
     wherefore
    0.36
    ftagPool
    0.36
    featureID
    0.36
     InputDecoration
    0.36
    Act Density 0.015%

    No Known Activations