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

    Neuronpedia

    INDEX
    Explanations

    criminal charges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     юриди
    0.70
    法律
    0.56
     juridique
    0.55
     jurídica
    0.52
     legale
    0.51
     LEGAL
    0.49
     ಕಾನೂ
    0.48
     कानूनी
    0.47
    司法
    0.47
     قانونی
    0.47
    POSITIVE LOGITS
     Child
    0.44
     brauch
    0.43
     charges
    0.43
     child
    0.42
     aggravated
    0.42
     D
    0.42
     assault
    0.41
     Mace
    0.41
    ディ
    0.39
     Jackson
    0.39
    Act Density 0.014%

    No Known Activations