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

    Neuronpedia

    INDEX
    Explanations

    actions and descriptions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Вы
    0.69
    out
    0.68
    paste
    0.67
     Па
    0.66
     Ин
    0.65
    product
    0.64
    punkt
    0.63
    Вы
    0.62
    fix
    0.62
    colors
    0.61
    POSITIVE LOGITS
     poss
    0.51
     significativa
    0.50
     effett
    0.50
     precisa
    0.49
     determin
    0.47
     rid
    0.44
     am
    0.44
     alternativa
    0.43
     curiosity
    0.42
     breeders
    0.42
    Act Density 0.000%

    No Known Activations