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

    Neuronpedia

    INDEX
    Explanations

    references to specific locations or environments

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

    locations and regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AttributeSet
    -0.58
    ніципалі
    -0.47
     occhiali
    -0.45
    hyrchwyd
    -0.44
     commerciali
    -0.43
    actéristi
    -0.43
     kesk
    -0.42
     möjligt
    -0.42
     ComVisible
    -0.42
     diamants
    -0.42
    POSITIVE LOGITS
    =$((
    0.46
    באנגלית
    0.44
    ]+=
    0.39
     BEHIND
    0.38
     שוליים
    0.37
    zzleHttp
    0.36
     ब्रेकडाउन
    0.36
     flan
    0.36
    <?>>
    0.36
     لئے
    0.35
    Act Density 0.064%

    No Known Activations