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

    Neuronpedia

    INDEX
    Explanations

    hus

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    s
    -0.06
    title
    -0.06
     захід
    -0.06
    ервые
    -0.06
     deficits
    -0.06
     Retrieved
    -0.06
     labelText
    -0.06
    f
    -0.05
    _iter
    -0.05
    em
    -0.05
    POSITIVE LOGITS
    θι
    0.07
    풍
    0.07
     bapt
    0.07
    ephir
    0.07
     واب
    0.07
    同学
    0.06
     stál
    0.06
    .Strict
    0.06
     wang
    0.06
     λόγ
    0.06
    Act Density 0.001%

    No Known Activations