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

    Neuronpedia

    INDEX
    Explanations

    indemnify, help, CRM

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝗬
    0.38
    ÈRES
    0.36
    繚
    0.35
    кти
    0.34
    ريكا
    0.34
    Gü
    0.34
    കളും
    0.34
    Kotlin
    0.34
    ുകളും
    0.33
    ισμού
    0.33
    POSITIVE LOGITS
    0.39
    </h2>
    0.37
    ``
    0.36
     refers
    0.35
     default
    0.33
     \
    0.32
     `
    0.32
     youngest
    0.32
    ="
    0.32
     ``
    0.32
    Act Density 0.344%

    No Known Activations