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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    The neuron is primarily picking up on first-person references (“I”, “am”, “not”, etc.) and self-descriptive statements by the author.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    427
    -0.06
     Memphis
    -0.06
     Barry
    -0.06
    Mu
    -0.06
     Symptoms
    -0.06
    forc
    -0.06
     Mu
    -0.06
     cis
    -0.06
     MH
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    _finder
    0.06
     bakımından
    0.06
     CREATED
    0.06
    RO
    0.06
    оген
    0.06
    empo
    0.06
    olo
    0.06
     deceit
    0.06
    producto
    0.06
     convolution
    0.06
    Act Density 0.092%

    No Known Activations