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

    Neuronpedia

    INDEX
    Explanations

    har

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the title “Mahabharata” (i.e. the segments of that name).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    安
    -0.06
     radiator
    -0.06
    .Initialize
    -0.06
     biological
    -0.06
     Tokens
    -0.06
     curt
    -0.06
    SqlServer
    -0.06
    魯
    -0.06
     Julius
    -0.06
    /buttons
    -0.06
    POSITIVE LOGITS
    -associated
    0.07
    _vector
    0.07
    ايد
    0.07
    acl
    0.07
     інтер
    0.06
    ských
    0.06
    (rp
    0.06
    .ibm
    0.06
    ipher
    0.06
     facet
    0.06
    Act Density 0.005%

    No Known Activations