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

    Neuronpedia

    INDEX
    Explanations

    mg

    np_max-act · gemini-2.0-flash

    The neuron never fires—it appears to be inactive and doesn’t detect any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    егор
    -0.06
    edium
    -0.06
    Escape
    -0.06
    ednou
    -0.06
    ARR
    -0.06
     Ελλην
    -0.06
    tel
    -0.06
    ΑΛ
    -0.06
     části
    -0.06
    ění
    -0.06
    POSITIVE LOGITS
     mg
    0.10
     Morgan
    0.09
     apprec
    0.08
     positive
    0.08
    MG
    0.07
     mil
    0.07
     (
    0.07
    .↵↵
    0.07
     MG
    0.07
     heavy
    0.07
    Act Density 0.009%

    No Known Activations