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

    Neuronpedia

    INDEX
    Explanations

    ethics and integrity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     en
    0.40
    és
    0.37
    ion
    0.36
    ha
    0.36
     are
    0.36
     Espagne
    0.35
    ong
    0.35
    -
    0.34
    ays
    0.33
    ayi
    0.33
    POSITIVE LOGITS
    eer
    0.44
    alten
    0.43
    本
    0.42
    我
    0.42
    自動
    0.40
    ме
    0.40
    uptime
    0.40
    ４
    0.39
    induction
    0.38
    omicron
    0.38
    Act Density 0.115%

    No Known Activations