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

    Neuronpedia

    INDEX
    Explanations

    GH

    np_max-act · gemini-2.0-flash

    The neuron responds to uppercase acronym‐style tokens (e.g. “U”, “GH”) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    licity
    -0.08
    alom
    -0.07
    uria
    -0.07
    оны
    -0.07
    них
    -0.07
    框
    -0.07
    хо
    -0.07
    woods
    -0.07
    &M
    -0.07
    Century
    -0.07
    POSITIVE LOGITS
     (?,
    0.06
     "),↵
    0.06
     %↵↵
    0.06
    '];
↵
    0.06
     mağ
    0.06
     %↵
    0.06
     @{↵
    0.06
     (£
    0.06
    ”。↵↵
    0.06
           
↵
    0.06
    Act Density 0.346%

    No Known Activations