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

    Neuronpedia

    INDEX
    Explanations

    quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oria
    -0.08
     COVID
    -0.07
    ecial
    -0.06
     equalTo
    -0.06
     своим
    -0.06
     Ves
    -0.06
     기준
    -0.06
    DIST
    -0.06
    ApiModelProperty
    -0.06
     pohy
    -0.06
    POSITIVE LOGITS
     Irish
    0.07
     stanice
    0.07
    ueil
    0.07
     Н
    0.07
     NS
    0.07
    ób
    0.07
    OLS
    0.07
    psz
    0.06
    legs
    0.06
     ними
    0.06
    Act Density 0.049%

    No Known Activations