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

    Neuronpedia

    INDEX
    Explanations

    diverse text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    вания
    -0.07
     Horde
    -0.06
     issued
    -0.06
    irates
    -0.06
     guilty
    -0.06
    ывания
    -0.06
    งแรก
    -0.06
     rare
    -0.06
     nackte
    -0.06
     측
    -0.06
    POSITIVE LOGITS
    (part
    0.06
     MSNBC
    0.06
     blitz
    0.06
    [label
    0.06
    _converter
    0.06
    .record
    0.06
    ccd
    0.06
    *f
    0.06
     initializer
    0.06
    (pf
    0.06
    Act Density 0.000%

    No Known Activations