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

    Neuronpedia

    INDEX
    Explanations

    racing events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     дек
    -0.07
    	retval
    -0.07
    658
    -0.07
     клу
    -0.07
     �
    -0.07
     прод
    -0.07
     від
    -0.06
     نوف
    -0.06
     Campo
    -0.06
     перев
    -0.06
    POSITIVE LOGITS
     пози
    0.07
     inFile
    0.06
    wave
    0.06
    =create
    0.06
     unused
    0.06
     supplying
    0.06
     قهر
    0.06
    trait
    0.06
    blob
    0.06
    ateř
    0.06
    Act Density 0.014%

    No Known Activations