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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BALL
    -0.08
     candles
    -0.07
     לידי
    -0.07
     pong
    -0.07
     teenagers
    -0.07
    Messages
    -0.07
     bagi
    -0.06
    .putString
    -0.06
     siding
    -0.06
     Boyd
    -0.06
    POSITIVE LOGITS
    建
    0.07
     elapsed
    0.07
    三大阶段
    0.07
     sue
    0.07
    contentType
    0.07
    建党
    0.06
    _ENABLED
    0.06
    	save
    0.06
     Hav
    0.06
     unavoidable
    0.06
    Act Density 0.020%

    No Known Activations