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

    Neuronpedia

    INDEX
    Explanations

    pruning trees and plants regularly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.93
    m
    0.81
     this
    0.80
    0
    0.76
    <0x80>
    0.73
     that
    0.73
    p
    0.72
     That
    0.70
    that
    0.70
    na
    0.66
    POSITIVE LOGITS
    л
    1.12
    ל
    1.09
     pruning
    0.89
    хай
    0.88
    Y
    0.82
    ка
    0.81
    رة
    0.78
    ценка
    0.74
    رت
    0.73
    мия
    0.73
    Act Density 0.004%

    No Known Activations