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

    Neuronpedia

    INDEX
    Explanations

    scientific studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PROFILE
    -0.07
     volume
    -0.07
     Finger
    -0.07
     persever
    -0.06
    compass
    -0.06
    60
    -0.06
    ゥ
    -0.06
     sinks
    -0.06
    _SLAVE
    -0.06
    Toy
    -0.06
    POSITIVE LOGITS
    ));//
    0.07
    웠
    0.06
    odu
    0.06
    0.06
     použit
    0.06
    $where
    0.06
    usunda
    0.06
    Personally
    0.06
    خب
    0.06
    .builder
    0.06
    Act Density 0.176%

    No Known Activations