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

    Neuronpedia

    INDEX
    Explanations

    ic

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on the word “cystic,” detecting occurrences of that specific term.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Goldberg
    -0.08
    /path
    -0.07
    -band
    -0.06
    ůr
    -0.06
     FORM
    -0.06
    Latin
    -0.06
    Providers
    -0.06
    ={`/
    -0.06
    _cores
    -0.06
    characters
    -0.06
    POSITIVE LOGITS
    ACE
    0.07
     Ос
    0.07
     паци
    0.07
     PSG
    0.07
    ancial
    0.07
    交流
    0.07
     communicating
    0.06
    al
    0.06
    ثال
    0.06
    acic
    0.06
    Act Density 0.001%

    No Known Activations