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

    Neuronpedia

    INDEX
    Explanations

    punishing someone or not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wit
    0.49
     ifs
    0.49
     Leslie
    0.47
     ach
    0.46
     해
    0.45
     Anglic
    0.44
     יו
    0.44
    ￡
    0.44
    เด็ก
    0.43
     ANGE
    0.43
    POSITIVE LOGITS
     continuando
    0.49
     comporta
    0.49
    galaxys
    0.47
    toluene
    0.44
    proton
    0.44
     diventare
    0.43
    izzando
    0.43
    િલ
    0.42
    ezing
    0.42
    pais
    0.42
    Act Density 0.000%

    No Known Activations