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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rl
    -0.07
    _validate
    -0.07
    _FACTOR
    -0.07
    暢
    -0.07
     proclaim
    -0.06
    _OPCODE
    -0.06
    :http
    -0.06
     gắn
    -0.06
     }:
    -0.06
    忖
    -0.06
    POSITIVE LOGITS
     Lexer
    0.07
    lands
    0.07
    浅
    0.06
    婪
    0.06
    -cart
    0.06
     bell
    0.06
     сделал
    0.06
     haunt
    0.06
    /options
    0.06
    实木
    0.06
    Act Density 0.000%

    No Known Activations