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

    Neuronpedia

    INDEX
    Explanations

    ine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vaugh
    -0.07
    amb
    -0.06
     Swamp
    -0.06
     saliva
    -0.06
     út
    -0.06
     Bucc
    -0.06
    onders
    -0.06
     volta
    -0.06
     devout
    -0.06
    ava
    -0.06
    POSITIVE LOGITS
     unlikely
    0.07
    час
    0.07
     gibt
    0.06
    unlikely
    0.06
    romise
    0.06
    редел
    0.06
     sust
    0.06
    Here
    0.06
    fadeIn
    0.06
    لیه
    0.06
    Act Density 0.001%

    No Known Activations