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

    Neuronpedia

    INDEX
    Explanations

    hexadecimal strings and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trö
    -0.88
     marchand
    -0.84
    voorbeeld
    -0.79
     partage
    -0.77
    avas
    -0.75
    VERTISING
    -0.75
     bekomme
    -0.74
     chaus
    -0.74
    ？　
    -0.72
     vedo
    -0.72
    POSITIVE LOGITS
    ideration
    1.09
     kunnen
    1.07
     annehmen
    1.05
     fijar
    0.95
    pée
    0.93
    اديم
    0.92
     pinggang
    0.91
    agie
    0.90
     anzunehmen
    0.89
     harán
    0.89
    Act Density 0.001%

    No Known Activations