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

    Neuronpedia

    INDEX
    Explanations

    AAAA

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reef
    -0.08
     agreg
    -0.07
    	menu
    -0.07
     ฮ
    -0.06
     Jed
    -0.06
     гід
    -0.06
    factory
    -0.06
     происходит
    -0.06
     JS
    -0.06
     stood
    -0.06
    POSITIVE LOGITS
    .blob
    0.07
    '{
    0.07
    _String
    0.06
     Rousse
    0.06
    lerdir
    0.06
     `"
    0.06
    _losses
    0.06
    .Protocol
    0.06
    _travel
    0.06
     dollar
    0.06
    Act Density 0.002%

    No Known Activations