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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _temp
    -0.07
    _stat
    -0.06
    	no
    -0.06
    _orders
    -0.06
     consoles
    -0.06
     rites
    -0.06
    _entry
    -0.06
     Verse
    -0.06
    ​↵↵
    -0.06
    여
    -0.06
    POSITIVE LOGITS
    @email
    0.07
    prisingly
    0.07
     mnist
    0.07
    (enc
    0.06
     Basel
    0.06
     �
    0.06
     HashMap
    0.06
     verde
    0.06
    ião
    0.06
    释
    0.06
    Act Density 0.020%

    No Known Activations