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

    Neuronpedia

    INDEX
    Explanations

    two-way communication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     saranam
    0.49
    ស្ស
    0.49
    znam
    0.46
    jour
    0.46
    sidenav
    0.46
     boots
    0.45
    t
    0.44
     kicks
    0.44
     panier
    0.44
    unjungi
    0.44
    POSITIVE LOGITS
    漑
    0.45
     Cardiff
    0.45
     बांट
    0.44
     Response
    0.43
    ینی
    0.43
    ικά
    0.43
    来看
    0.42
     Tunisian
    0.42
     Batter
    0.42
    ifelse
    0.42
    Act Density 0.002%

    No Known Activations