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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    乡
    -0.08
    ‌↵↵
    -0.08
     उन्ह
    -0.07
     pres
    -0.07
    ದೆ
    -0.07
     endless
    -0.07
     blind
    -0.07
    šnj
    -0.07
    illong
    -0.07
     cup
    -0.07
    POSITIVE LOGITS
     plugged
    0.08
    পার
    0.08
     lasers
    0.07
    VERSION
    0.07
     plugging
    0.07
     liggen
    0.07
    Бұл
    0.07
    Collateral
    0.07
     వరకు
    0.07
     IMPORTANT
    0.07
    Act Density 0.051%

    No Known Activations