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

    Neuronpedia

    INDEX
    Explanations

    G7 discussion or a fact about biology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    可谓
    0.44
     pemasaran
    0.44
     ingestion
    0.44
     (“
    0.43
     intakes
    0.43
     (‘
    0.43
     ide
    0.42
     Aman
    0.42
     enabling
    0.41
     lipids
    0.40
    POSITIVE LOGITS
    modulo
    0.50
    residual
    0.48
    même
    0.47
    fonction
    0.46
     risultato
    0.45
    effetto
    0.44
    Avec
    0.44
     résultat
    0.43
    ี่ย
    0.43
    wild
    0.43
    Act Density 0.007%

    No Known Activations