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

    Neuronpedia

    INDEX
    Explanations

    transfer of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    n
    1.69
    s
    1.63
    I
    1.59
    B
    1.57
    S
    1.50
    on
    1.47
    T
    1.42
    A
    1.38
    x
    1.36
    C
    1.33
    POSITIVE LOGITS
     trabajado
    1.05
     necessario
    0.95
    ৫
    0.89
    -"+
    0.88
     കൂടുതല്‍
    0.84
     necessário
    0.82
     cercano
    0.82
    ায়
    0.81
    Ŷ
    0.80
     maestro
    0.80
    Act Density 0.000%

    No Known Activations