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

    Neuronpedia

    INDEX
    Explanations

    possibilities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    智能
    -0.07
     trapping
    -0.07
    (B
    -0.06
    �
    -0.06
    ör
    -0.06
    ore
    -0.06
    (m
    -0.06
    (Bundle
    -0.06
    _m
    -0.06
     바
    -0.06
    POSITIVE LOGITS
    *****/↵
    0.06
     तन
    0.06
     WiFi
    0.06
    turn
    0.06
    承
    0.06
    ':"
    0.06
     bulletin
    0.06
     yyyy
    0.06
     dan
    0.06
     melee
    0.06
    Act Density 0.082%

    No Known Activations