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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    看你
    -0.07
     AMC
    -0.07
     dank
    -0.07
    Narrated
    -0.06
    Dimension
    -0.06
    emic
    -0.06
    inc
    -0.06
    ضبط
    -0.06
    힉
    -0.06
     getAddress
    -0.06
    POSITIVE LOGITS
    _PP
    0.08
    .stat
    0.07
     jede
    0.07
    _linked
    0.07
     discontinued
    0.06
     свое
    0.06
     nerve
    0.06
    霞
    0.06
    _toggle
    0.06
    _signal
    0.06
    Act Density 0.038%

    No Known Activations