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

    Neuronpedia

    INDEX
    Explanations

    positions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     KBS
    -0.07
    nob
    -0.07
    _transactions
    -0.06
    Rp
    -0.06
     Modes
    -0.06
     звичай
    -0.06
     masa
    -0.06
     proponents
    -0.06
    spoken
    -0.06
    níky
    -0.06
    POSITIVE LOGITS
     moyen
    0.07
    asons
    0.07
    .CLIENT
    0.06
     powerful
    0.06
    เกษตร
    0.06
    poster
    0.06
     حرفه
    0.06
     Garrett
    0.06
     �
    0.06
     firing
    0.06
    Act Density 0.000%

    No Known Activations