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

    Neuronpedia

    INDEX
    Explanations

    reasoning gun violence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     बिन
    0.72
     surround
    0.69
     surrounds
    0.67
     FO
    0.64
     Compat
    0.63
    بل
    0.63
     விளை
    0.58
     произведения
    0.58
    dison
    0.57
    昧
    0.56
    POSITIVE LOGITS
    oku
    0.61
    닝
    0.60
    హా
    0.60
     bébé
    0.60
     lógico
    0.58
    oxet
    0.58
     dibujo
    0.58
    萼
    0.57
     noires
    0.57
     perder
    0.56
    Act Density 0.183%

    No Known Activations