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

    Neuronpedia

    INDEX
    Explanations

    lib

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vaugh
    -0.07
    (customer
    -0.07
     če
    -0.07
     FIR
    -0.07
     dům
    -0.07
    +",
    -0.06
    andatory
    -0.06
    ++;↵
    -0.06
    ...↵↵↵
    -0.06
    ++);↵
    -0.06
    POSITIVE LOGITS
    _responses
    0.06
     alive
    0.06
    _logic
    0.06
    лер
    0.06
    elia
    0.06
     pathlib
    0.06
     суб
    0.06
     replies
    0.06
     floatValue
    0.06
    lab
    0.06
    Act Density 0.003%

    No Known Activations