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

    Neuronpedia

    INDEX
    Explanations

    above

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    guenos
    -0.70
     supérieurs
    -0.69
    berdayakan
    -0.68
    SequentialGroup
    -0.67
    timbangkan
    -0.67
    Билгалдахарш
    -0.66
     nôtre
    -0.64
     igång
    -0.64
    __(/*!
    -0.64
     Vikipedi
    -0.63
    POSITIVE LOGITS
     body
    0.54
     size
    0.52
     pit
    0.50
     barrel
    0.50
     meat
    0.50
     wax
    0.49
     vessel
    0.48
     long
    0.48
     buffer
    0.47
     jar
    0.47
    Act Density 0.027%

    No Known Activations