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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    驱
    -0.07
    ومان
    -0.07
    _meter
    -0.07
    вин
    -0.06
     disputes
    -0.06
    xFFF
    -0.06
     scandals
    -0.06
     vlá
    -0.06
     замен
    -0.06
    >::
    -0.06
    POSITIVE LOGITS
     ||↵
    0.06
    .amazonaws
    0.06
     production
    0.06
    <(),
    0.06
     published
    0.06
     reinforcement
    0.06
     OUT
    0.06
     variation
    0.06
     harb
    0.06
     yet
    0.06
    Act Density 0.018%

    No Known Activations