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

    Neuronpedia

    INDEX
    Explanations

    conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    twenty
    -0.06
    شاه
    -0.06
    もう
    -0.06
     longitudinal
    -0.06
    Hier
    -0.06
    至少
    -0.06
    _gem
    -0.06
    xford
    -0.06
     whim
    -0.06
    _LOW
    -0.06
    POSITIVE LOGITS
    _hat
    0.07
     ng
    0.06
     Promo
    0.06
    UEL
    0.06
    _hosts
    0.06
     краще
    0.06
     área
    0.06
     pensar
    0.06
    .JOptionPane
    0.06
    ヌ
    0.06
    Act Density 0.004%

    No Known Activations