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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oshi
    -0.07
     Ж
    -0.07
     εφαρ
    -0.07
    .MATCH
    -0.07
    Boost
    -0.06
     Take
    -0.06
     speeches
    -0.06
    声明
    -0.06
    ського
    -0.06
    ž
    -0.06
    POSITIVE LOGITS
     hect
    0.07
    warts
    0.06
    ुरस
    0.06
    HTTP
    0.06
    ้เก
    0.06
    403
    0.06
    стория
    0.06
    ク
    0.06
    /stdc
    0.06
     shale
    0.06
    Act Density 0.001%

    No Known Activations