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

    Neuronpedia

    INDEX
    Explanations

    forcing players

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    0.63
     manzanas
    0.53
    पल
    0.51
     vidro
    0.49
    Dots
    0.48
     whack
    0.48
     pantalones
    0.48
    ER
    0.47
    🄴
    0.47
     dhad
    0.46
    POSITIVE LOGITS
    矿
    0.42
     duplicating
    0.40
     гаран
    0.40
     सकती
    0.40
    arran
    0.40
    的可能性
    0.40
    icht
    0.39
    的服务
    0.39
     سکتی
    0.39
     тариф
    0.39
    Act Density 0.001%

    No Known Activations