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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    '#
    -0.08
     Broad
    -0.07
    vn
    -0.07
     iceberg
    -0.07
    익
    -0.07
    _ctl
    -0.07
     Bran
    -0.07
     desir
    -0.07
     大
    -0.07
     lame
    -0.07
    POSITIVE LOGITS
    টির
    0.09
     اینکه
    0.09
     stimuli
    0.09
     melihat
    0.08
     необходимости
    0.08
     adanya
    0.08
    িভ
    0.08
     footage
    0.08
     необходимость
    0.08
     tanta
    0.08
    Act Density 0.014%

    No Known Activations