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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash

    This neuron responds to filmmaking direction and shot‐description terms (e.g. “Break,” “Shot,” “Close‐up,” “Establishing shot”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     zn
    -0.07
    (edit
    -0.07
     Persist
    -0.06
     cour
    -0.06
    unta
    -0.06
     scr
    -0.06
     Mét
    -0.06
     Tunisia
    -0.06
    itted
    -0.06
     fraudulent
    -0.06
    POSITIVE LOGITS
     लगभग
    0.07
    .partner
    0.07
     unbiased
    0.06
     MessageBoxButtons
    0.06
     />)↵
    0.06
    _Component
    0.06
    >"↵
    0.06
     DAN
    0.06
    -fill
    0.06
    LOOD
    0.06
    Act Density 0.101%

    No Known Activations