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

    Neuronpedia

    INDEX
    Explanations

    equals

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _template
    -0.07
    .INPUT
    -0.07
    _example
    -0.06
     converters
    -0.06
    	handle
    -0.06
    void
    -0.06
     Chun
    -0.06
    compose
    -0.06
    ових
    -0.06
     subscribe
    -0.06
    POSITIVE LOGITS
     ».
    0.07
    mmo
    0.06
    难
    0.06
     wit
    0.06
    ινε
    0.06
     Eisen
    0.06
     mails
    0.06
     blackjack
    0.06
    ,UnityEngine
    0.06
     &_
    0.06
    Act Density 0.086%

    No Known Activations