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

    Neuronpedia

    INDEX
    Explanations

    the word "features"

    oai_token-act-pair · gemini-2.0-flash

    features

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.97
     rempliss
    -0.96
     refroid
    -0.94
    berdayakan
    -0.86
    bibinfo
    -0.84
     conservé
    -0.84
     refusé
    -0.81
     supprim
    -0.81
    tvguidetime
    -0.79
     fallu
    -0.79
    POSITIVE LOGITS
    ce
    0.65
    وار
    0.54
    ст
    0.54
     Talis
    0.52
    Read
    0.52
                      
    0.51
    cles
    0.51
     exhaustive
    0.51
    Clik
    0.51
                   
    0.50
    Act Density 2.707%

    No Known Activations