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

    Neuronpedia

    INDEX
    Explanations

    bos

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     חמ
    -0.08
    iquement
    -0.08
    Singer
    -0.08
     Oster
    -0.07
     देशों
    -0.07
     самостоятель
    -0.07
     inédit
    -0.07
     Clap
    -0.07
     lure
    -0.07
    Switcher
    -0.07
    POSITIVE LOGITS
    /her
    0.11
     fallu
    0.09
    'll
    0.09
     தனது
    0.08
     himself
    0.08
    hrte
    0.08
     കൂട
    0.08
    hr
    0.08
     Majesty
    0.08
     bonke
    0.07
    Act Density 0.666%

    No Known Activations