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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     xv
    -0.07
    joint
    -0.06
     ape
    -0.06
     Operator
    -0.06
    "^
    -0.06
     maur
    -0.06
    actual
    -0.06
    �
    -0.06
    _msgs
    -0.06
     tướng
    -0.06
    POSITIVE LOGITS
    	UI
    0.06
     compel
    0.06
     lazım
    0.06
    放
    0.06
     Snape
    0.06
     safely
    0.06
    .FormattingEnabled
    0.06
     щоб
    0.06
    LING
    0.06
    _ENV
    0.06
    Act Density 0.106%

    No Known Activations