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

    Neuronpedia

    INDEX
    Explanations

    smooth, differentiable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     UAE
    -0.07
     cof
    -0.07
    ामन
    -0.07
    Apollo
    -0.07
    observable
    -0.06
    udiant
    -0.06
    Foo
    -0.06
     tripod
    -0.06
     NOR
    -0.06
     Raven
    -0.06
    POSITIVE LOGITS
    Exceptions
    0.08
    _update
    0.07
    iß
    0.07
    .RequestMethod
    0.07
    anga
    0.07
    cash
    0.07
    IntoConstraints
    0.06
    registration
    0.06
     fiss
    0.06
     %↵↵
    0.06
    Act Density 0.010%

    No Known Activations