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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Pool
    -0.07
     gó
    -0.07
    Put
    -0.06
     😀
    -0.06
    “That
    -0.06
     Modeling
    -0.06
    ┃
    -0.06
    "When
    -0.06
     brutal
    -0.06
    (item
    -0.06
    POSITIVE LOGITS
     kleine
    0.07
    LoginForm
    0.06
     aff
    0.06
     lar
    0.06
    _Admin
    0.06
     frat
    0.06
    -в
    0.06
     tangent
    0.06
     partial
    0.06
    .Accessible
    0.06
    Act Density 0.007%

    No Known Activations