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

    Neuronpedia

    INDEX
    Explanations

    unit, id

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ḥ
    1.34
    ⾃
    1.30
    Self
    1.30
     Self
    1.30
    En
    1.28
     Company
    1.27
    Super
    1.26
    ⼦
    1.26
    Ge
    1.25
    My
    1.24
    POSITIVE LOGITS
     york
    1.39
     pierre
    1.29
     luna
    1.28
     american
    1.28
     johnson
    1.27
     washington
    1.27
     california
    1.26
     italy
    1.24
     berlin
    1.23
     france
    1.21
    Act Density 1.421%

    No Known Activations