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

    Neuronpedia

    INDEX
    Explanations

    mathematical arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -transparent
    -0.08
     Pine
    -0.08
    amel
    -0.07
     שב
    -0.07
     Neal
    -0.07
     breach
    -0.07
     Tattoo
    -0.07
     accidental
    -0.06
     Khal
    -0.06
     compared
    -0.06
    POSITIVE LOGITS
    lıklar
    0.07
    ואה
    0.07
     نفسها
    0.07
     להתמוד
    0.07
    徇
    0.07
    🤲
    0.06
    موت
    0.06
    Tür
    0.06
     sorte
    0.06
    삘
    0.06
    Act Density 0.062%

    No Known Activations