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

    Neuronpedia

    INDEX
    Explanations

    actions affecting objects

    np_max-act · gemini-2.0-flash

    This neuron detects gerund verbs (–ing forms) that describe the main functional purpose or use of an invention (e.g. transporting, storing, bundling, displaying, restraining).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    카라
    -0.07
    ytut
    -0.07
    座
    -0.06
     ولم
    -0.06
     及
    -0.06
    íny
    -0.06
    사이
    -0.06
    iktig
    -0.06
     opendir
    -0.06
     số
    -0.06
    POSITIVE LOGITS
    Overrides
    0.07
     Member
    0.07
     excit
    0.06
     baseline
    0.06
     league
    0.06
     frontend
    0.06
     Basic
    0.06
     compliment
    0.06
    .Parcel
    0.06
     remed
    0.06
    Act Density 0.054%

    No Known Activations