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

    Neuronpedia

    INDEX
    Explanations

    Coding/data processing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _EL
    -0.07
     필요한
    -0.07
    otos
    -0.07
     Geb
    -0.07
    excerpt
    -0.06
     mM
    -0.06
    税务局
    -0.06
    _ref
    -0.06
     voy
    -0.06
    _EV
    -0.06
    POSITIVE LOGITS
     Hip
    0.07
    骂
    0.07
    劝
    0.07
    -color
    0.06
     extent
    0.06
    개
    0.06
    portion
    0.06
    大股东
    0.06
     bacter
    0.06
     automation
    0.06
    Act Density 0.230%

    No Known Activations