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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act · gemini-2.0-flash

    This neuron detects phrases that describe large-scale spatial extents or proportions—e.g. “big,” “taking up most of the city block,” “covering two floors.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    د
    -0.07
    kommen
    -0.07
     embrace
    -0.07
    _doc
    -0.06
     我
    -0.06
     intentional
    -0.06
    cod
    -0.06
    (error
    -0.06
    Pos
    -0.06
    ":-
    -0.06
    POSITIVE LOGITS
     Nicola
    0.07
     ocup
    0.06
     zor
    0.06
     krb
    0.06
    +'&
    0.06
    umo
    0.06
    _kelas
    0.06
    damage
    0.06
    Publication
    0.06
     क
    0.06
    Act Density 0.032%

    No Known Activations