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

    Neuronpedia

    INDEX
    Explanations

    where

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "},
    -0.07
    "-
    -0.07
    umably
    -0.07
     λέ
    -0.07
    .",
    -0.07
    istence
    -0.06
     presumably
    -0.06
    normalized
    -0.06
     Например
    -0.06
    »,
    -0.06
    POSITIVE LOGITS
    oce
    0.06
    prises
    0.06
     ))}↵
    0.06
    ۳۰
    0.06
    iming
    0.06
    (sin
    0.06
    issions
    0.06
     öz
    0.06
     unregister
    0.06
    fone
    0.06
    Act Density 0.000%

    No Known Activations