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

    Neuronpedia

    INDEX
    Explanations

    plural suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bil
    -0.07
     Pt
    -0.07
     dividends
    -0.06
     Agility
    -0.06
    eným
    -0.06
     fir
    -0.06
    .setup
    -0.06
    (times
    -0.06
     United
    -0.06
    .square
    -0.06
    POSITIVE LOGITS
     جديد
    0.07
     нем
    0.06
     Tokens
    0.06
    aman
    0.06
    خرى
    0.06
    ardin
    0.06
    _TYPES
    0.06
    िकल
    0.06
    _SOC
    0.06
    イド
    0.06
    Act Density 0.092%

    No Known Activations