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

    Neuronpedia

    INDEX
    Explanations

    constructor parameters and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     applaud
    0.41
     funcione
    0.40
     prepping
    0.40
    営業時間
    0.39
     nesses
    0.39
     wirelessly
    0.38
    vetica
    0.38
     outage
    0.37
     applauded
    0.37
     ejec
    0.37
    POSITIVE LOGITS
    Graduate
    0.44
    Parent
    0.42
    鋆
    0.41
     Graduate
    0.41
    äger
    0.40
    继承
    0.40
    Creat
    0.40
    Ancient
    0.40
    Jud
    0.39
     stink
    0.39
    Act Density 0.000%

    No Known Activations