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

    Neuronpedia

    INDEX
    Explanations

    Go

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     valu
    -0.07
     };
    -0.06
     \
    -0.06
    婆
    -0.06
    _algorithm
    -0.06
    опри
    -0.06
     King
    -0.06
     PK
    -0.06
    _Pl
    -0.06
     rot
    -0.06
    POSITIVE LOGITS
    结束
    0.07
     اتحاد
    0.07
     لس
    0.06
    ματα
    0.06
     khô
    0.06
     γλώ
    0.06
     fencing
    0.06
     StringBuffer
    0.06
     perfectly
    0.06
    ];↵↵↵
    0.06
    Act Density 0.026%

    No Known Activations