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

    Neuronpedia

    INDEX
    Explanations

    Alignment

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    orsi
    -0.07
    .crop
    -0.06
    咡
    -0.06
     mụ
    -0.06
    	record
    -0.06
    可以更好
    -0.06
    }$/
    -0.06
    lip
    -0.06
    rh
    -0.06
     Citadel
    -0.06
    POSITIVE LOGITS
    #![
    0.07
     Киев
    0.07
    Inicial
    0.07
    _SPI
    0.07
     Start
    0.07
    ()=>{↵
    0.07
    Restricted
    0.07
    ASHINGTON
    0.07
    _paid
    0.07
     Born
    0.07
    Act Density 0.001%

    No Known Activations