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

    Neuronpedia

    INDEX
    Explanations

    club

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    来源
    -0.08
    ిస్త
    -0.08
    امة
    -0.08
    ిస్తుంది
    -0.08
    اريخ
    -0.08
     prophet
    -0.08
     elde
    -0.08
     снима
    -0.07
     originated
    -0.07
     históricos
    -0.07
    POSITIVE LOGITS
     TAP
    0.08
    avat
    0.08
     دوستان
    0.08
    rate
    0.08
     exploration
    0.07
     Ging
    0.07
    xing
    0.07
    etz
    0.07
    _TRA
    0.07
     Sakura
    0.07
    Act Density 0.005%

    No Known Activations