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

    Neuronpedia

    INDEX
    Explanations

    file paths and errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :“
    0.40
    ้ย
    0.36
    cadilly
    0.32
    ktCap
    0.31
    :”
    0.31
    ებისთვის
    0.30
    ityanath
    0.30
    :":
    0.30
     कुलकर्णी
    0.30
    getRadius
    0.30
    POSITIVE LOGITS
    黑
    0.27
    javase
    0.27
    Ха
    0.27
     काले
    0.27
    ex
    0.26
    Hor
    0.26
    H
    0.26
     s
    0.26
    bi
    0.26
    mod
    0.25
    Act Density 0.024%

    No Known Activations