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

    Neuronpedia

    INDEX
    Explanations

    under

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ń
    -0.07
     Frid
    -0.07
    ARR
    -0.07
     ner
    -0.07
    -screen
    -0.07
    プリン
    -0.07
    otoxic
    -0.07
    ñas
    -0.06
    になってしまう
    -0.06
    -pr
    -0.06
    POSITIVE LOGITS
    _atom
    0.08
    树脂
    0.07
     candle
    0.07
     Ride
    0.07
    镜头
    0.07
     something
    0.07
     felt
    0.07
    		
↵
↵
    0.07
     עסק
    0.06
    앖
    0.06
    Act Density 0.015%

    No Known Activations