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

    Neuronpedia

    INDEX
    Explanations

    references to model classes in programming or software development contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    modelmodel identifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /**
    -0.58
    antMatchers
    -0.49
     BorderSide
    -0.47
    Spoljašnje
    -0.46
    basicConfig
    -0.46
    abbix
    -0.44
    fillType
    -0.44
     ואת
    -0.43
    Kaynakça
    -0.43
    zości
    -0.43
    POSITIVE LOGITS
    Model
    2.27
     Model
    1.77
    MODEL
    1.22
     MODEL
    1.21
    ModelList
    1.16
    Models
    1.08
    BaseModel
    1.07
     Models
    1.06
    UserModel
    1.05
    setModel
    1.03
    Act Density 0.006%

    No Known Activations