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

    Neuronpedia

    INDEX
    Explanations

    image descriptions

    np_max-act · gemini-2.0-flash

    This neuron activates on words that reference or introduce visual data or imagery—terms like graph, data, shows, picture, drew, photo, etc.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    oji
    -0.07
    unks
    -0.07
     relaxation
    -0.07
    _SETUP
    -0.06
    IH
    -0.06
     store
    -0.06
    ify
    -0.06
    ifies
    -0.06
    ording
    -0.06
     Desire
    -0.06
    POSITIVE LOGITS
     GestureDetector
    0.07
     Vari
    0.06
     editar
    0.06
    .AllowGet
    0.06
     striped
    0.06
     Serv
    0.06
    ?>"↵
    0.06
    ickým
    0.06
    表现
    0.06
    ován
    0.06
    Act Density 0.077%

    No Known Activations