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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     epsilon
    -0.07
     chassis
    -0.07
    ния
    -0.07
    .bindingNavigatorMove
    -0.06
    (PC
    -0.06
    ForgeryToken
    -0.06
    (foo
    -0.06
    eda
    -0.06
     languages
    -0.06
    rowsable
    -0.06
    POSITIVE LOGITS
     helpers
    0.06
    ==↵
    0.06
     invalidated
    0.06
     Мор
    0.06
    ORM
    0.06
     Error
    0.06
     juicy
    0.06
    _ACCEPT
    0.06
     choice
    0.06
     Literal
    0.06
    Act Density 0.001%

    No Known Activations