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

    Neuronpedia

    INDEX
    Explanations

    Code/technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    subscriber
    -0.07
    منت
    -0.07
    γού
    -0.07
    ESP
    -0.07
    adero
    -0.06
    //------------------------------------------------------------------------------↵↵
    -0.06
    -direction
    -0.06
    isecond
    -0.06
    _DIAG
    -0.06
    фик
    -0.06
    POSITIVE LOGITS
    估
    0.07
     whites
    0.07
     clearTimeout
    0.06
     공부
    0.06
    	name
    0.06
     acclaim
    0.06
     PartialEq
    0.06
     admitting
    0.06
     meds
    0.06
    Hola
    0.06
    Act Density 7.162%

    No Known Activations