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

    Neuronpedia

    INDEX
    Explanations

    en

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,size
    -0.07
    $data
    -0.07
     inval
    -0.06
     survival
    -0.06
    >"
↵
    -0.06
    ниця
    -0.06
     boarding
    -0.06
     kvm
    -0.06
     fv
    -0.06
    类型
    -0.06
    POSITIVE LOGITS
     Chen
    0.08
    екар
    0.07
     Peterson
    0.07
    ปฏ
    0.07
    chrom
    0.07
    Sen
    0.07
     edil
    0.06
    ič
    0.06
    aled
    0.06
     Rud
    0.06
    Act Density 0.002%

    No Known Activations