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

    Neuronpedia

    INDEX
    Explanations

    43

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    addSub
    0.65
     ACCESS
    0.63
    Southeast
    0.63
    sub
    0.63
     access
    0.63
    access
    0.62
     accesso
    0.62
     subst
    0.62
    imsu
    0.61
     sub
    0.61
    POSITIVE LOGITS
    Fe
    0.71
     fases
    0.70
    镓
    0.65
     Fe
    0.65
     fréquentes
    0.63
    уна
    0.62
    珽
    0.58
     caratteristiche
    0.57
     Adopt
    0.56
    ಙ
    0.56
    Act Density 0.186%

    No Known Activations