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

    Neuronpedia

    INDEX
    Explanations

    flatten

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the word “flatten” (and its variants like “flat,” “flattened,” “flatten()”)—i.e. it detects mentions of a flattening operation.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Sin
    -0.07
    Half
    -0.07
     ambitious
    -0.06
    asıyla
    -0.06
    Deep
    -0.06
     Mi
    -0.06
    ication
    -0.06
     uri
    -0.06
    Tek
    -0.06
     Maria
    -0.06
    POSITIVE LOGITS
    ным
    0.07
    智能
    0.06
     FCC
    0.06
    .dataGridView
    0.06
     bodily
    0.06
     settle
    0.06
     fencing
    0.06
     ağ
    0.06
     settling
    0.06
     countryside
    0.06
    Act Density 0.005%

    No Known Activations