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

    Neuronpedia

    INDEX
    Explanations

    non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zkou
    -0.06
    .assertIs
    -0.06
    EEDED
    -0.06
    に出
    -0.06
    _Normal
    -0.06
    σή
    -0.06
     originates
    -0.06
    brains
    -0.06
    stantiate
    -0.06
    .Debugger
    -0.06
    POSITIVE LOGITS
     ".$
    0.07
    弘
    0.07
    ีฬา
    0.07
    lete
    0.07
     simultaneous
    0.07
     vol
    0.06
    etro
    0.06
     �
    0.06
     располож
    0.06
     "+"
    0.06
    Act Density 0.018%

    No Known Activations