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

    Neuronpedia

    INDEX
    Explanations

    creative brand names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uggish
    0.29
    requently
    0.29
    gruntled
    0.29
    Ln
    0.27
    acterial
    0.26
     unusually
    0.26
    paralleled
    0.26
    ammable
    0.26
    viously
    0.26
    licting
    0.26
    POSITIVE LOGITS
    क्लेव
    0.31
    prüsü
    0.30
     दीवाना
    0.30
     sueños
    0.29
     rebels
    0.28
     gráficos
    0.28
     Itália
    0.28
     सॉल्यू
    0.28
     ganó
    0.27
     começ
    0.27
    Act Density 0.005%

    No Known Activations