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

    Neuronpedia

    INDEX
    Explanations

    gli

    np_max-act · gemini-2.0-flash

    This neuron is primarily activated by occurrences of the brain‐cancer term “glioblastoma” (and related substrings like “glioma”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    олос
    -0.07
    .Pattern
    -0.07
     lavender
    -0.06
    ody
    -0.06
     untreated
    -0.06
    AspectRatio
    -0.06
    ального
    -0.06
    ály
    -0.06
    _VERSION
    -0.06
    ensburg
    -0.06
    POSITIVE LOGITS
     gli
    0.07
     Killing
    0.07
     инвести
    0.07
     Dumbledore
    0.07
     мис
    0.06
     raising
    0.06
     Mine
    0.06
     hypothetical
    0.06
     happily
    0.06
    piece
    0.06
    Act Density 0.003%

    No Known Activations