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

    Neuronpedia

    INDEX
    Explanations

    informal language and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ๘
    0.49
    하였다
    0.48
    ทาง
    0.47
    ân
    0.44
     နှင့်
    0.42
     الضرب
    0.41
    加以
    0.41
    nCount
    0.41
    เพียง
    0.40
    ;<
    0.40
    POSITIVE LOGITS
     literally
    0.84
     fuck
    0.82
     fucked
    0.82
     fucking
    0.81
     idk
    0.79
     lmao
    0.79
     shit
    0.75
     Literally
    0.73
    literally
    0.72
     shitty
    0.71
    Act Density 0.042%

    No Known Activations