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

    Neuronpedia

    INDEX
    Explanations

    numerals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Micha
    -0.07
    Hyper
    -0.07
    нося
    -0.07
     доход
    -0.07
     inflammatory
    -0.06
     mue
    -0.06
     ALPHA
    -0.06
    ằm
    -0.06
     sunrise
    -0.06
     flush
    -0.06
    POSITIVE LOGITS
     직접
    0.06
    ':[
    0.06
    features
    0.06
    jid
    0.06
     Docker
    0.06
    reflect
    0.06
    =""/>↵
    0.06
    .total
    0.06
     honest
    0.06
     explodes
    0.06
    Act Density 0.013%

    No Known Activations