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

    Neuronpedia

    INDEX
    Explanations

    various text snippets

    np_max-act · gemini-2.0-flash

    The neuron spikes on terms describing the coding and blinding of specimens or data in a scientific methods context.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     трьох
    -0.06
     knight
    -0.06
    상품
    -0.06
     Reconstruction
    -0.06
     cooldown
    -0.06
     punishing
    -0.06
    �
    -0.06
     descend
    -0.06
     Orchestra
    -0.06
     cabins
    -0.06
    POSITIVE LOGITS
    .func
    0.07
    ってる
    0.07
    atz
    0.07
     Mutual
    0.06
    äd
    0.06
    ontology
    0.06
    erving
    0.06
    aturally
    0.06
     спря
    0.06
     wanting
    0.06
    Act Density 0.148%

    No Known Activations