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

    Neuronpedia

    INDEX
    Explanations

    OS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .parameter
    -0.07
     SX
    -0.07
     scarf
    -0.07
    Decrypt
    -0.06
     theft
    -0.06
    flip
    -0.06
    Toast
    -0.06
     Vect
    -0.06
     acces
    -0.06
     Daten
    -0.06
    POSITIVE LOGITS
    _SECTION
    0.07
    lbrakk
    0.07
     Dos
    0.07
     січня
    0.06
    ARS
    0.06
     Iowa
    0.06
    shed
    0.06
     Colorado
    0.06
    .App
    0.06
    _ANDROID
    0.06
    Act Density 0.002%

    No Known Activations