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

    Neuronpedia

    INDEX
    Explanations

    included

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oggle
    -0.07
     ary
    -0.06
    Canonical
    -0.06
     kaç
    -0.06
     '*'
    -0.06
    _XML
    -0.06
     lover
    -0.06
     guaranteed
    -0.06
    ’ét
    -0.06
     backlash
    -0.06
    POSITIVE LOGITS
    _WORK
    0.07
    _generated
    0.06
    ouch
    0.06
     Masks
    0.06
    ージ
    0.06
     Lung
    0.06
     plaque
    0.06
    .quality
    0.06
     HuffPost
    0.06
    (filters
    0.06
    Act Density 0.083%

    No Known Activations