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

    Neuronpedia

    INDEX
    Explanations

    streak

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    269
    -0.07
    _CONV
    -0.06
     �
    -0.06
    297
    -0.06
    /^
    -0.06
    asar
    -0.06
    мати
    -0.06
    toHaveBeenCalledTimes
    -0.06
    发出
    -0.06
     domest
    -0.06
    POSITIVE LOGITS
     streak
    0.11
     fast
    0.07
     tendencies
    0.07
     traceback
    0.06
    搬
    0.06
    ọng
    0.06
    �
    0.06
    (seed
    0.06
    评
    0.06
     ="";↵
    0.06
    Act Density 0.005%

    No Known Activations