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

    Neuronpedia

    INDEX
    Explanations

    secret key configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Runs
    0.41
    フラー
    0.38
    手数料
    0.38
     Prevention
    0.38
    wala
    0.37
     Preservation
    0.37
    💰
    0.37
     Education
    0.35
    TextureData
    0.35
    ”…
    0.35
    POSITIVE LOGITS
     diagnose
    0.41
     +"
    0.39
     Gerv
    0.38
    ViewById
    0.37
     diag
    0.37
     वेग
    0.36
     przyp
    0.35
    itamins
    0.35
    बर्ट
    0.35
    vinced
    0.35
    Act Density 0.000%

    No Known Activations