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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -functions
    -0.06
     Filters
    -0.06
    .postMessage
    -0.06
     Failed
    -0.06
    рос
    -0.06
    ulum
    -0.06
    	union
    -0.06
    .deep
    -0.06
     creepy
    -0.06
     Kids
    -0.06
    POSITIVE LOGITS
    (ids
    0.07
    _FRIEND
    0.07
    合同
    0.07
     řád
    0.06
     agendas
    0.06
    (bar
    0.06
    (range
    0.06
    Bitcoin
    0.06
     harmon
    0.06
     debit
    0.06
    Act Density 0.013%

    No Known Activations