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

    Neuronpedia

    INDEX
    Explanations

    below the body part

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    вел
    0.90
     possa
    0.89
     eyew
    0.88
     ocular
    0.87
     morn
    0.87
     pueda
    0.86
     geral
    0.86
     Prueba
    0.85
     consol
    0.84
     obra
    0.84
    POSITIVE LOGITS
    광
    0.83
     Dimit
    0.77
     коэффициент
    0.77
    銅
    0.72
    attempt
    0.69
    堂
    0.68
    ného
    0.68
    𝗦
    0.67
     tropes
    0.66
    olič
    0.66
    Act Density 0.001%

    No Known Activations