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

    Neuronpedia

    INDEX
    Explanations

    Detecting code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Barrier
    -0.06
    (pk
    -0.06
    ikki
    -0.06
     trip
    -0.06
    ripp
    -0.06
    trigger
    -0.06
     Auss
    -0.06
    defer
    -0.06
     bạc
    -0.06
     Frame
    -0.06
    POSITIVE LOGITS
     Pastor
    0.06
    trusted
    0.06
     darken
    0.06
     quando
    0.06
     predetermined
    0.06
    -install
    0.06
     wear
    0.06
    :description
    0.06
    践
    0.06
     uplift
    0.06
    Act Density 0.000%

    No Known Activations