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

    Neuronpedia

    INDEX
    Explanations

    choices and options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fuselage
    0.47
     callous
    0.47
    รถ
    0.43
     bolas
    0.43
     be
    0.42
     пом
    0.41
     童
    0.41
    WE
    0.40
     jagged
    0.40
    boli
    0.39
    POSITIVE LOGITS
     available
    0.55
     Available
    0.55
     Options
    0.55
     Option
    0.54
     option
    0.54
    ти
    0.52
     opções
    0.52
     disponíveis
    0.50
     options
    0.49
     earthqu
    0.49
    Act Density 0.016%

    No Known Activations