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

    Neuronpedia

    INDEX
    Explanations

    target

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of HTML “target=” attributes (e.g. target="_blank").

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Indies
    -0.07
     endwhile
    -0.07
    луги
    -0.07
     Brewer
    -0.07
     sprint
    -0.07
    naz
    -0.06
     dod
    -0.06
     rebuild
    -0.06
    _widget
    -0.06
    justify
    -0.06
    POSITIVE LOGITS
    ẳn
    0.07
    .outputs
    0.07
     McD
    0.06
     Transparency
    0.06
    rouw
    0.06
     피
    0.06
     Neh
    0.06
    át
    0.06
     Accessories
    0.06
    amm
    0.06
    Act Density 0.001%

    No Known Activations