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

    Neuronpedia

    INDEX
    Explanations

    borders

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Yale
    -0.07
    亦
    -0.07
     CS
    -0.06
     Minnesota
    -0.06
     Developers
    -0.06
    .F
    -0.06
     leicht
    -0.06
     KL
    -0.06
     mirrors
    -0.06
    STITUTE
    -0.06
    POSITIVE LOGITS
     sev
    0.07
     squid
    0.07
    ([]);↵↵
    0.06
    烧
    0.06
     ());↵↵
    0.06
    .FindAsync
    0.06
     penal
    0.06
    ("""↵
    0.06
    _combo
    0.06
    fruit
    0.06
    Act Density 0.144%

    No Known Activations