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

    Neuronpedia

    INDEX
    Explanations

    slots

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    USIC
    -0.07
    acular
    -0.07
     מערכת
    -0.07
     אמנ
    -0.07
    잽
    -0.06
    תכ
    -0.06
    asterxml
    -0.06
     credential
    -0.06
     cam
    -0.06
    书房
    -0.06
    POSITIVE LOGITS
     declining
    0.09
    ('?
    0.08
     '/'
    0.07
    Cos
    0.07
    _atts
    0.07
    _quality
    0.07
     hes
    0.07
    发生
    0.07
    bst
    0.07
    兹
    0.06
    Act Density 0.012%

    No Known Activations