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

    Neuronpedia

    INDEX
    Explanations

    feedback on english phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    I
    0.53
    一
    0.50
    大きい
    0.47
    サイクル
    0.46
    んだ
    0.46
    2
    0.46
    corresponding
    0.45
     tmp
    0.45
     spectre
    0.45
     กม
    0.45
    POSITIVE LOGITS
     bisque
    0.52
     Detox
    0.51
     cayenne
    0.50
     Sunrise
    0.49
    zó
    0.48
     Cea
    0.48
     Sumatra
    0.47
     Cec
    0.47
     Dalai
    0.47
     Mad
    0.46
    Act Density 0.001%

    No Known Activations