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
     Melissa
    -0.08
     万円
    -0.08
     OSS
    -0.07
     erection
    -0.06
    　　　　
    -0.06
     स
    -0.06
     Jared
    -0.06
     في
    -0.06
     toured
    -0.06
     Ω
    -0.06
    POSITIVE LOGITS
     getDefault
    0.07
     skeletons
    0.06
     fireworks
    0.06
     continual
    0.06
    .vol
    0.06
     scrutiny
    0.06
    _play
    0.06
    �
    0.06
     aliqua
    0.06
     졸
    0.06
    Act Density 0.001%

    No Known Activations