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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aşırı
    -0.07
    划
    -0.06
     보
    -0.06
     peeled
    -0.06
     whereabouts
    -0.06
    观
    -0.06
     comfy
    -0.06
    _PE
    -0.06
    ях
    -0.06
    ;border
    -0.06
    POSITIVE LOGITS
     creating
    0.08
    ple
    0.07
    (sym
    0.06
    Framework
    0.06
    -leading
    0.06
    iple
    0.06
    _param
    0.06
    .labelControl
    0.06
     lines
    0.06
     legislation
    0.06
    Act Density 0.000%

    No Known Activations