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

    Neuronpedia

    INDEX
    Explanations

    experimental groupings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     сум
    -0.07
     Lots
    -0.06
    servers
    -0.06
     Scroll
    -0.06
     Đại
    -0.06
    telefone
    -0.06
     티
    -0.06
     Mã
    -0.06
     visiting
    -0.06
    Sweet
    -0.06
    POSITIVE LOGITS
    _REGISTRY
    0.07
    ILITY
    0.06
    _Reset
    0.06
    -NLS
    0.06
     lange
    0.06
    Ｙ
    0.06
    ge
    0.06
    ’ї
    0.06
    no
    0.06
     Simpson
    0.06
    Act Density 0.038%

    No Known Activations