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

    Neuronpedia

    INDEX
    Explanations

    $$

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Clare
    -0.08
    Fri
    -0.08
     Fran
    -0.08
     Tr
    -0.08
     Lent
    -0.07
     Kral
    -0.07
     Amph
    -0.07
    itele
    -0.07
     train
    -0.07
    lit
    -0.07
    POSITIVE LOGITS
    244
    0.07
    ({"
    0.06
    ions
    0.06
    .ManyToManyField
    0.06
    IONS
    0.06
     greatly
    0.06
    .destination
    0.06
     Morrow
    0.06
    0.06
    YGON
    0.06
    Act Density 0.008%

    No Known Activations