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

    Neuronpedia

    INDEX
    Explanations

    fortune cookies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dignity
    -0.06
    [element
    -0.06
     podstat
    -0.06
    }`;↵↵
    -0.06
     lockdown
    -0.06
    就算
    -0.06
     NaN
    -0.06
     itself
    -0.06
     대부분
    -0.06
    >>
    -0.06
    POSITIVE LOGITS
    ोह
    0.07
    غ
    0.07
    amura
    0.07
    (serv
    0.07
    ása
    0.07
    诉
    0.07
     chuyên
    0.07
     kéo
    0.06
    ku
    0.06
    ��
    0.06
    Act Density 0.001%

    No Known Activations