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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash

    This neuron never fires— it’s effectively a dead neuron that doesn’t detect any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     told
    -0.07
     SMP
    -0.06
    県
    -0.06
    ันน
    -0.06
    투
    -0.06
    Ele
    -0.06
    atas
    -0.06
     англ
    -0.06
     vej
    -0.06
    Generator
    -0.06
    POSITIVE LOGITS
     mů
    0.07
     것도
    0.07
    […]
    0.06
    $sub
    0.06
    تف
    0.06
    ("-",
    0.06
     دیگری
    0.06
    ****************************************
    0.06
     porous
    0.06
     vars
    0.06
    Act Density 0.001%

    No Known Activations