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

    Neuronpedia

    INDEX
    Explanations

    access

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gst
    -0.08
     Jenn
    -0.07
    إيم
    -0.07
     Trio
    -0.07
    ⌈
    -0.07
    暖气
    -0.07
    ступ
    -0.06
     Jes
    -0.06
     извест
    -0.06
     album
    -0.06
    POSITIVE LOGITS
    定
    0.07
    า
    0.07
    צטר
    0.07
    쳐
    0.07
     Strap
    0.07
    Batch
    0.07
    fcc
    0.07
    _partition
    0.07
    .YEAR
    0.07
     cedar
    0.07
    Act Density 0.007%

    No Known Activations