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

    Neuronpedia

    INDEX
    Explanations

    Code definitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _inf
    -0.06
     جمهوری
    -0.06
    nd
    -0.06
     اط
    -0.06
     Вели
    -0.06
    	spec
    -0.06
    <boolean
    -0.06
    Ctrl
    -0.06
     intents
    -0.06
     кін
    -0.06
    POSITIVE LOGITS
     가져
    0.07
     generally
    0.06
    '].'
    0.06
    odeled
    0.06
    abella
    0.06
     farewell
    0.06
    .abstract
    0.06
    .EventHandler
    0.06
    _Variable
    0.06
    >
↵
    0.06
    Act Density 0.012%

    No Known Activations