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

    Neuronpedia

    INDEX
    Explanations

    legal codes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     internal
    -0.07
    	part
    -0.06
     guts
    -0.06
     стати
    -0.06
     �
    -0.06
     tisí
    -0.06
     Wings
    -0.06
    ışman
    -0.06
    LU
    -0.06
     estilo
    -0.06
    POSITIVE LOGITS
    urchased
    0.08
     Shiite
    0.07
    俄
    0.06
    ющих
    0.06
     obtaining
    0.06
     информа
    0.06
     Bruno
    0.06
    243
    0.06
     Nor
    0.06
    enin
    0.06
    Act Density 0.005%

    No Known Activations