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

    Neuronpedia

    INDEX
    Explanations

    IMF

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    綜合
    -0.08
    º
    -0.07
    轨道
    -0.07
     combust
    -0.07
    (tasks
    -0.07
    情境
    -0.07
     eup
    -0.06
    ampions
    -0.06
    胜负
    -0.06
    无障碍
    -0.06
    POSITIVE LOGITS
     كما
    0.07
    삠
    0.07
    pora
    0.07
     Doctors
    0.07
     cougar
    0.07
     statist
    0.07
     באר
    0.07
     razón
    0.07
     Bitcoin
    0.07
     hen
    0.07
    Act Density 0.005%

    No Known Activations