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

    Neuronpedia

    INDEX
    Explanations

    30

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     whites
    -0.07
    ,in
    -0.07
    Rule
    -0.06
    )',
    -0.06
    ]},
    -0.06
     Pole
    -0.06
    MATCH
    -0.06
    دي
    -0.06
     
    -0.06
     intake
    -0.06
    POSITIVE LOGITS
     Zealand
    0.06
    htub
    0.06
    -detail
    0.06
    _ANDROID
    0.06
     تفاوت
    0.06
     Крім
    0.06
    Exam
    0.06
    ोफ
    0.06
    .Default
    0.06
     SERIES
    0.06
    Act Density 0.000%

    No Known Activations