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

    Neuronpedia

    INDEX
    Explanations

    Starting to be

    np_max-act · gemini-2.0-flash

    The neuron fires strongly on multi‐word progressive transition phrases that signal escalation or change of state—e.g. “getting to a point where…” or “starting to get messy.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    bt
    -0.06
     foil
    -0.06
    雨
    -0.06
     restTemplate
    -0.06
     bake
    -0.06
    dal
    -0.06
    ió
    -0.06
    MET
    -0.06
    トル
    -0.06
     duk
    -0.06
    POSITIVE LOGITS
     dní
    0.07
    	pub
    0.07
     mænd
    0.06
    arlar
    0.06
    лять
    0.06
     ApplicationRecord
    0.06
     wealthy
    0.06
     shapes
    0.06
    序
    0.06
     мова
    0.06
    Act Density 0.104%

    No Known Activations