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

    Neuronpedia

    INDEX
    Explanations

    onto

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on occurrences of the directional preposition “onto.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     in
    -0.12
    In
    -0.11
     в
    -0.10
    -in
    -0.09
     In
    -0.09
    in
    -0.09
     IN
    -0.09
    _In
    -0.08
    _in
    -0.08
    14
    -0.08
    POSITIVE LOGITS
     onto
    0.13
    onto
    0.07
    ulta
    0.07
     countert
    0.07
     oto
    0.07
    @nate
    0.07
    터
    0.07
     doğr
    0.07
    ">'.$
    0.07
     upto
    0.07
    Act Density 0.006%

    No Known Activations