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

    Neuronpedia

    INDEX
    Explanations

    showing progress

    np_max-act · gemini-2.0-flash

    The neuron detects words and phrases related to giving user feedback on status or progress (e.g. “informed,” “status,” “progress,” “feedback”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     functor
    -0.07
    engan
    -0.06
    itus
    -0.06
     initiation
    -0.06
    .btn
    -0.06
     paper
    -0.06
    urse
    -0.06
     compel
    -0.06
     biopsy
    -0.06
    .Un
    -0.06
    POSITIVE LOGITS
    .loader
    0.07
     OSError
    0.07
    /library
    0.07
     เช
    0.06
    over
    0.06
     웹사이트
    0.06
     αυ
    0.06
     San
    0.06
     explos
    0.06
     연
    0.06
    Act Density 0.030%

    No Known Activations