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

    Neuronpedia

    INDEX
    Explanations

    prepositions and punctuation

    np_max-act · gemini-2.0-flash

    The neuron is triggered by common function words and discourse markers (especially prepositions like “in,” subordinating conjunctions like “if,” “as,” “of,” and punctuation like commas).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Critical
    -0.07
     C
    -0.06
    ाखण
    -0.06
     N
    -0.06
     Lot
    -0.06
    ौ
    -0.06
     E
    -0.06
     tangent
    -0.06
    289
    -0.06
     burning
    -0.06
    POSITIVE LOGITS
    beam
    0.06
    -Pro
    0.06
    .Ticks
    0.06
    !.↵↵
    0.06
     BIOS
    0.06
    ModelCreating
    0.06
    _GUI
    0.06
    '))->
    0.06
    pez
    0.06
    _temp
    0.06
    Act Density 0.032%

    No Known Activations