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

    Neuronpedia

    INDEX
    Explanations

    positive adjectives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     انقل
    -0.07
    cação
    -0.07
    арт
    -0.07
     didSet
    -0.06
     Sew
    -0.06
    _preview
    -0.06
     tooltips
    -0.06
    .ComboBoxStyle
    -0.06
     мир
    -0.06
    ्ल
    -0.06
    POSITIVE LOGITS
    upported
    0.07
    ALIGN
    0.07
     please
    0.07
    _DELETED
    0.06
     étaient
    0.06
    jf
    0.06
    -motion
    0.06
     찾
    0.06
    Loads
    0.06
     might
    0.06
    Act Density 0.054%

    No Known Activations