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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    лением
    -0.08
    .Iterator
    -0.07
     çöz
    -0.06
    措
    -0.06
    !='
    -0.06
    子供
    -0.06
    etheus
    -0.06
    ляться
    -0.06
     Relatives
    -0.06
    kol
    -0.06
    POSITIVE LOGITS
    ,.
    0.07
    .Pr
    0.07
     Rt
    0.07
     ACT
    0.06
     A
    0.06
    .HeaderText
    0.06
    (cert
    0.06
    739
    0.06
     arch
    0.06
    .borderColor
    0.06
    Act Density 0.030%

    No Known Activations