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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    仲
    -0.06
     Nimbus
    -0.06
     Cad
    -0.06
    итися
    -0.06
     shoved
    -0.06
    jpg
    -0.06
    anol
    -0.06
     enslaved
    -0.05
     KV
    -0.05
    sst
    -0.05
    POSITIVE LOGITS
     ere
    0.08
    0.07
    ('.')[
    0.07
     自动生成
    0.07
    █
    0.07
    <?>
    0.07
    phthalm
    0.07
     Голов
    0.07
     ".",
    0.07
    -awesome
    0.07
    Act Density 0.017%

    No Known Activations