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

    Neuronpedia

    INDEX
    Explanations

    difficult to compete

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     прия
    0.40
    час
    0.39
    rice
    0.39
    ly
    0.38
     оказывается
    0.37
     সুনাম
    0.37
    appa
    0.37
    โบ
    0.37
    ipps
    0.37
    enação
    0.37
    POSITIVE LOGITS
     berbahaya
    0.43
    dessus
    0.42
    퀀
    0.40
    Dangerous
    0.40
    ┛
    0.40
     šk
    0.39
     مزاج
    0.39
     ABOVE
    0.38
    董
    0.38
    感受到
    0.37
    Act Density 0.000%

    No Known Activations