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

    Neuronpedia

    INDEX
    Explanations

    persona and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     భాగంగా
    0.45
    Float
    0.42
    float
    0.37
     Float
    0.37
    getFullName
    0.37
    ʕ
    0.37
    FLOAT
    0.36
    _{-}$
    0.36
     రాజ్య
    0.35
    чат
    0.35
    POSITIVE LOGITS
     entries
    0.43
     Mason
    0.43
     harvest
    0.42
    akes
    0.42
     DMC
    0.41
     gradio
    0.40
     mason
    0.38
    పా
    0.38
     ode
    0.37
    udahan
    0.36
    Act Density 0.004%

    No Known Activations