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

    Neuronpedia

    INDEX
    Explanations

    tree/trees

    np_max-act · gemini-2.0-flash

    The neuron activates on references to trees and tree‐related terms (e.g. planting, roots, pits, removal, arboretum, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Eval
    -0.08
     účast
    -0.06
    WARE
    -0.06
    load
    -0.06
    防
    -0.06
    LOAD
    -0.06
     streamed
    -0.06
    ництва
    -0.06
     dirt
    -0.06
    awk
    -0.06
    POSITIVE LOGITS
    ῶ
    0.07
    рез
    0.06
     Energy
    0.06
    /commons
    0.06
    _ov
    0.06
    acb
    0.06
    阳
    0.06
    }},
    0.06
    161
    0.06
     UFO
    0.06
    Act Density 0.008%

    No Known Activations