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

    Neuronpedia

    INDEX
    Explanations

    coercion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     تصو
    -0.07
     gol
    -0.07
     fundamental
    -0.07
    kemiz
    -0.07
     язы
    -0.07
    われる
    -0.07
     منتشر
    -0.07
     unfinished
    -0.07
     nap
    -0.06
    들은
    -0.06
    POSITIVE LOGITS
     coercion
    0.13
     coerc
    0.11
     coerce
    0.09
     coer
    0.07
    coc
    0.06
    -orange
    0.06
    ectar
    0.06
    	Action
    0.06
    CSR
    0.06
     weird
    0.06
    Act Density 0.001%

    No Known Activations