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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .after
    -0.07
    aszt
    -0.07
     Random
    -0.07
    onzo
    -0.07
     etwa
    -0.07
     Klein
    -0.07
     حالة
    -0.07
    .option
    -0.07
    ப்படி
    -0.07
     notable
    -0.07
    POSITIVE LOGITS
     licensors
    0.09
     домой
    0.08
     Soul
    0.08
     doucement
    0.08
     вперед
    0.08
     vì
    0.08
     buzzing
    0.08
    Acknowled
    0.08
     stakeholders
    0.08
     pren
    0.07
    Act Density 0.001%

    No Known Activations