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

    Neuronpedia

    INDEX
    Explanations

    code/database

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lah
    -0.07
    (Group
    -0.07
     سوم
    -0.06
    -learning
    -0.06
    ore
    -0.06
     SharedModule
    -0.06
    าช
    -0.06
    того
    -0.06
    πο
    -0.06
    лат
    -0.06
    POSITIVE LOGITS
    _hold
    0.06
    VERIFY
    0.06
     iliş
    0.06
     via
    0.06
     VERIFY
    0.06
     Fortunately
    0.06
    认
    0.06
    ！↵↵↵↵
    0.06
    –and
    0.06
    (Blueprint
    0.06
    Act Density 0.002%

    No Known Activations