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

    Neuronpedia

    INDEX
    Explanations

    Numbers with "000"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fero
    -0.08
     автора
    -0.08
     человека
    -0.08
    ייבן
    -0.08
    然
    -0.08
     surrendered
    -0.08
     рамках
    -0.08
    idd
    -0.07
    息
    -0.07
     опух
    -0.07
    POSITIVE LOGITS
     workplace
    0.08
     hake
    0.08
     salad
    0.08
     shore
    0.07
     turnover
    0.07
    spd
    0.07
     mila
    0.07
    ured
    0.07
     turnovers
    0.07
     outdoor
    0.07
    Act Density 0.031%

    No Known Activations