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

    Neuronpedia

    INDEX
    Explanations

    Shakiness, Shakuntala, Shakadang, Shakshuka, Shakira

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    يت
    1.36
    人
    1.23
    tól
    1.12
    يس
    1.10
    يات
    1.09
    stücke
    1.06
    ről
    1.05
    ية
    1.04
    يف
    1.04
    ци
    1.02
    POSITIVE LOGITS
     אחד
    1.20
    AD
    1.19
    য়
    1.18
     blockbuster
    1.17
    ED
    1.16
     masterpiece
    1.14
     symposium
    1.09
    IL
    1.07
    OD
    1.06
     vastu
    1.05
    Act Density 0.000%

    No Known Activations