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

    Neuronpedia

    INDEX
    Explanations

    export default

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Def
    0.94
     Defaults
    0.92
    Def
    0.89
    Defaults
    0.83
     defaults
    0.79
     def
    0.76
    defaults
    0.76
     Defin
    0.75
    def
    0.74
     DEF
    0.72
    POSITIVE LOGITS
    疸
    0.41
    ക്കാ
    0.37
    жают
    0.37
     gelungen
    0.37
    фов
    0.36
    aufgaben
    0.35
    export
    0.35
    вают
    0.35
     samud
    0.35
    েক
    0.34
    Act Density 0.007%

    No Known Activations