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

    Neuronpedia

    INDEX
    Explanations

    pressure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    럴
    -0.07
    amerate
    -0.06
     чтобы
    -0.06
    @nate
    -0.06
    센
    -0.06
    -axis
    -0.06
    _old
    -0.06
    кие
    -0.06
     NOM
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    produ
    0.07
     органи
    0.07
     broker
    0.07
    ा.↵
    0.07
    (o
    0.07
    .DO
    0.07
    .resource
    0.07
    /manage
    0.06
    ै.↵
    0.06
    (strict
    0.06
    Act Density 0.004%

    No Known Activations