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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash

    analogs that compare technology and software processes to relatable real-world scenarios or activities.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron primarily activates on mentions of “hair.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	fs
    -0.07
     которую
    -0.06
     в
    -0.06
     Purchase
    -0.06
    desired
    -0.06
    Crit
    -0.06
    firefox
    -0.06
    Case
    -0.06
    	P
    -0.06
     cenu
    -0.06
    POSITIVE LOGITS
     biography
    0.07
     좋은
    0.07
    .Normalize
    0.07
    ùi
    0.06
     clin
    0.06
     tokenizer
    0.06
    orman
    0.06
    .Ş
    0.06
    genre
    0.06
    VES
    0.06
    Act Density 0.222%

    No Known Activations