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

    Neuronpedia

    INDEX
    Explanations

    //

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    介绍
    -0.07
     Fetish
    -0.07
     problemas
    -0.06
     kommen
    -0.06
     것은
    -0.06
    める
    -0.06
     stature
    -0.06
    Thus
    -0.06
    _PART
    -0.06
     Pero
    -0.06
    POSITIVE LOGITS
    .profile
    0.08
     περι
    0.07
    hazi
    0.07
    =('
    0.06
    죠
    0.06
     ува
    0.06
    ница
    0.06
     bb
    0.06
    нив
    0.06
    	bg
    0.06
    Act Density 0.000%

    No Known Activations