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

    Neuronpedia

    INDEX
    Explanations

    articles/contractions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ")"↵
    -0.07
     hoping
    -0.06
     quake
    -0.06
     interested
    -0.06
     rocking
    -0.06
     để
    -0.06
    .meta
    -0.06
    enumerate
    -0.06
     determine
    -0.06
     unfortunate
    -0.06
    POSITIVE LOGITS
    рия
    0.07
    .bunifu
    0.07
    寄
    0.06
    _factors
    0.06
    _rel
    0.06
    elin
    0.06
    νας
    0.06
    маз
    0.06
    _run
    0.06
    ्रश
    0.06
    Act Density 0.422%

    No Known Activations