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

    Neuronpedia

    INDEX
    Explanations

    code structures and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Public
    1.12
    Ε
    0.94
    **.
    0.90
     publice
    0.89
    "'
    0.89
    ideas
    0.88
    ἐ
    0.87
    Islam
    0.86
    essay
    0.86
    ージュ
    0.84
    POSITIVE LOGITS
     bool
    2.46
     float
    2.39
     int
    2.24
    bool
    2.22
     void
    2.12
    float
    2.08
     boolean
    1.95
     uint
    1.82
    void
    1.79
    int
    1.74
    Act Density 0.328%

    No Known Activations