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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GRES
    -0.07
    モデル
    -0.07
    У
    -0.06
     polynomial
    -0.06
     Floral
    -0.06
    ์ร
    -0.06
    _analysis
    -0.06
    nět
    -0.06
     Modelo
    -0.06
    .UNRELATED
    -0.06
    POSITIVE LOGITS
     предлож
    0.07
     introducing
    0.07
     stringent
    0.07
    思想
    0.07
     suiv
    0.06
    {@
    0.06
     다운받
    0.06
    cmc
    0.06
     sei
    0.06
    possibly
    0.06
    Act Density 0.016%

    No Known Activations