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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    The neuron is selectively activating on occurrences of the word “information” (and closely related diffusion-context terms).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    �
    -0.07
     Comet
    -0.06
    >{
    -0.06
     Від
    -0.06
     instructional
    -0.06
     таб
    -0.06
     crude
    -0.06
    усти
    -0.06
    ']])↵
    -0.06
     inequality
    -0.06
    POSITIVE LOGITS
     proje
    0.07
     cinco
    0.07
     pleasantly
    0.06
    	gl
    0.06
     Bellev
    0.06
     whim
    0.06
     gelen
    0.06
     Serie
    0.06
    ـ
    0.06
     linspace
    0.06
    Act Density 0.101%

    No Known Activations