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

    Neuronpedia

    INDEX
    Explanations

    parity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Гор
    -0.07
    ɡ
    -0.07
     Southeast
    -0.07
    blob
    -0.07
     Killing
    -0.07
     Leading
    -0.07
    غذي
    -0.07
     Ray
    -0.07
     TextField
    -0.07
    𝇊
    -0.07
    POSITIVE LOGITS
    שוקולד
    0.08
    是你
    0.07
    *)↵↵
    0.07
    stände
    0.07
    (character
    0.07
    הצלחה
    0.07
    per
    0.07
    ╊
    0.07
     perpetrated
    0.07
     aspirations
    0.07
    Act Density 0.005%

    No Known Activations