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

    Neuronpedia

    INDEX
    Explanations

    ions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wreckage
    -0.07
     عراق
    -0.07
     Marine
    -0.07
    策
    -0.07
     behaviors
    -0.06
     지나
    -0.06
     cloudy
    -0.06
     grads
    -0.06
    َا
    -0.06
    訓
    -0.06
    POSITIVE LOGITS
    ammable
    0.07
    Aws
    0.06
    sword
    0.06
    	entry
    0.06
     😀
    0.06
    Overflow
    0.06
    Fizz
    0.06
    orns
    0.06
    COPY
    0.06
     Lol
    0.06
    Act Density 0.001%

    No Known Activations