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

    Neuronpedia

    INDEX
    Explanations

    material

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ait
    1.06
     pă
    1.01
     iba
    0.99
     harte
    0.96
    𝚓
    0.96
     باقي
    0.95
     valuable
    0.95
     Valuable
    0.95
    //!
    0.94
     Famous
    0.92
    POSITIVE LOGITS
    mersible
    1.16
    lardan
    1.14
    ية
    1.12
    tela
    1.06
    erp
    1.05
    ੀ
    1.04
    个
    1.04
    in
    1.04
    er
    0.99
    rangian
    0.98
    Act Density 0.000%

    No Known Activations