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

    Neuronpedia

    INDEX
    Explanations

    names or labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    വസ്ഥ
    0.75
     habló
    0.71
     lectured
    0.67
     majeure
    0.66
     beschäftigen
    0.66
    erval
    0.65
    oxylated
    0.64
     maje
    0.64
     sağlar
    0.64
    Value
    0.62
    POSITIVE LOGITS
     moniker
    1.88
     nicknames
    1.85
     nickname
    1.82
     alias
    1.70
     shortened
    1.70
     aliases
    1.69
     abbreviation
    1.67
     acronym
    1.61
     branding
    1.53
    nickname
    1.49
    Act Density 1.478%

    No Known Activations