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

    Neuronpedia

    INDEX
    Explanations

    search for resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     impresora
    1.28
     établir
    1.28
    1.24
     colère
    1.22
     Bücher
    1.19
     imprimir
    1.18
     balle
    1.17
    শনের
    1.17
    肨
    1.16
    䅡
    1.16
    POSITIVE LOGITS
    预
    1.01
     predict
    1.01
     forecast
    0.98
     ا
    0.98
    pred
    0.97
     decoy
    0.96
     reward
    0.95
     prep
    0.94
     prognosis
    0.94
     fet
    0.91
    Act Density 0.158%

    No Known Activations