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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron responds to personal‐narrative subject pronouns (e.g. “we,” “they”) introducing actions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     や
    -0.07
    _relation
    -0.07
    −
    -0.07
     musicians
    -0.07
     theory
    -0.07
    acity
    -0.07
    .exception
    -0.07
    -btn
    -0.07
     Мініст
    -0.07
     Cove
    -0.07
    POSITIVE LOGITS
    елеф
    0.06
    vj
    0.06
     @{$
    0.06
     frankfurt
    0.06
    ้เก
    0.06
     conspic
    0.06
     ket
    0.06
     Conor
    0.06
     squ
    0.06
     CLEAR
    0.05
    Act Density 0.029%

    No Known Activations