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

    Neuronpedia

    INDEX
    Explanations

    gun control legislation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    부터
    1.09
     détente
    1.09
    ร
    1.05
    ل
    1.03
     domination
    0.97
    到达
    0.94
    いた
    0.93
    রের
    0.92
    饺
    0.91
    경기
    0.90
    POSITIVE LOGITS
    fi
    1.07
    q
    1.02
    ter
    1.00
    music
    0.98
    fq
    0.96
    3
    0.95
    flex
    0.94
    fin
    0.93
    2
    0.93
    chik
    0.92
    Act Density 0.001%

    No Known Activations