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

    Neuronpedia

    INDEX
    Explanations

    B

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     дія
    -0.07
     пункт
    -0.07
    .array
    -0.07
     "_
    -0.07
     предмет
    -0.06
     itens
    -0.06
     unity
    -0.06
     incomplete
    -0.06
     حالت
    -0.06
    улю
    -0.06
    POSITIVE LOGITS
    .no
    0.07
    queda
    0.06
    (GL
    0.06
    (bus
    0.06
     whereas
    0.06
    王
    0.06
     Stanford
    0.05
    と
    0.05
     上海
    0.05
     weap
    0.05
    Act Density 0.000%

    No Known Activations