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

    Neuronpedia

    INDEX
    Explanations

    diacritics in different languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tra
    -0.08
     நோ
    -0.08
    trib
    -0.08
     TRA
    -0.08
    -0.08
     kilos
    -0.08
     טרא
    -0.07
     kato
    -0.07
     لوی
    -0.07
    horn
    -0.07
    POSITIVE LOGITS
     Grund
    0.08
     Crock
    0.08
    URIComponent
    0.07
     Normalize
    0.07
    urrence
    0.07
     senator
    0.07
    incerely
    0.07
     Subscribe
    0.07
     admire
    0.07
     ordinal
    0.07
    Act Density 0.000%
    No Known Activations