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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ']}↵
    -0.08
     gì
    -0.07
    }}}
    -0.07
    }).
    -0.07
    BCM
    -0.07
    ании
    -0.07
    "]),
    -0.07
    تأسي
    -0.07
    '}}↵
    -0.07
    对不起
    -0.07
    POSITIVE LOGITS
    簧
    0.07
     зуб
    0.07
     hairstyles
    0.07
    YL
    0.07
    折磨
    0.07
    -R
    0.07
     кров
    0.06
    ייס
    0.06
    置いて
    0.06
     замеча
    0.06
    Act Density 0.003%

    No Known Activations