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

    Neuronpedia

    INDEX
    Explanations

    in or within

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utilizzando
    0.30
     rilev
    0.30
     dejando
    0.29
     sorprendente
    0.29
    机会
    0.28
     siguiendo
    0.28
    em
    0.27
     poniendo
    0.27
     dettagli
    0.27
    ла
    0.27
    POSITIVE LOGITS
    0.29
     bowels
    0.28
    טר
    0.26
    מד
    0.25
    ется
    0.24
    ע
    0.24
     the
    0.23
     at
    0.23
     was
    0.23
     Domains
    0.23
    Act Density 3.645%

    No Known Activations