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

    Neuronpedia

    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     obscene
    -0.07
     slide
    -0.07
     Been
    -0.07
    Family
    -0.07
     Hang
    -0.06
    _yield
    -0.06
    ♀♀♀♀
    -0.06
     contentType
    -0.06
    seek
    -0.06
     Darkness
    -0.06
    POSITIVE LOGITS
     prostě
    0.07
    жди
    0.06
     elbow
    0.06
    ैठक
    0.06
    ский
    0.06
     пищ
    0.06
     그녀의
    0.06
     materi
    0.06
    \Context
    0.06
    ORIA
    0.06
    Act Density 0.017%

    No Known Activations