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

    Neuronpedia

    INDEX
    Explanations

    without

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hygiene
    -0.06
     XYZ
    -0.06
     网
    -0.06
    だろう
    -0.06
     Worship
    -0.06
    igg
    -0.06
     BigDecimal
    -0.06
    _battery
    -0.06
    .best
    -0.06
    .Widget
    -0.06
    POSITIVE LOGITS
     Without
    0.08
     without
    0.07
    without
    0.07
     seins
    0.07
     Lic
    0.06
    健康
    0.06
    efully
    0.06
    FieldName
    0.06
    کس
    0.06
    rosso
    0.06
    Act Density 0.024%

    No Known Activations