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

    Neuronpedia

    INDEX
    Explanations

    animal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rz
    -0.07
    (big
    -0.07
     evenings
    -0.07
     rej
    -0.07
     recordings
    -0.07
     land
    -0.06
     sä
    -0.06
     esos
    -0.06
    四个自信
    -0.06
    🥜
    -0.06
    POSITIVE LOGITS
    .ActionBar
    0.08
    צב
    0.07
     técnico
    0.07
     durable
    0.07
    tom
    0.07
    _year
    0.07
    三条
    0.07
    】
    0.07
    ohan
    0.07
     Count
    0.07
    Act Density 0.009%

    No Known Activations