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

    Neuronpedia

    INDEX
    Explanations

    Discussions and defining concepts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    chips
    -0.09
    chip
    -0.08
     nouveaux
    -0.08
     Massa
    -0.08
    rices
    -0.08
    Chip
    -0.08
     ions
    -0.08
    mainder
    -0.08
    Knife
    -0.08
     депутат
    -0.08
    POSITIVE LOGITS
     considerando
    0.09
     perspective
    0.08
     estamos
    0.08
     betrachten
    0.08
     metric
    0.08
     viewpoint
    0.08
    すると
    0.08
    (metric
    0.08
     necessariamente
    0.08
     nəz
    0.08
    Act Density 0.058%

    No Known Activations