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

    Neuronpedia

    INDEX
    Explanations

    technical specifications and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𒊩
    0.91
    ମ୍
    0.88
     diminue
    0.83
    mujer
    0.82
     mulheres
    0.80
    áfico
    0.80
     seksual
    0.80
    URCH
    0.79
     musst
    0.79
    ссий
    0.77
    POSITIVE LOGITS
     J
    0.74
     T
    0.71
     chip
    0.70
     few
    0.65
    -
    0.64
     R
    0.64
     Z
    0.64
     probing
    0.63
     $\
    0.62
    Cl
    0.62
    Act Density 0.001%

    No Known Activations