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

    Neuronpedia

    INDEX
    Explanations

    complexity and relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vaguely
    0.40
     orthon
    0.40
     enth
    0.38
    лесо
    0.37
     loosely
    0.37
     antiguos
    0.36
     regulars
    0.36
     suppos
    0.35
     Skywalker
    0.35
    ⁿ
    0.35
    POSITIVE LOGITS
    課
    0.40
    ới
    0.38
    রাং
    0.38
    texttt
    0.37
     vra
    0.36
    års
    0.36
    inese
    0.36
     своим
    0.36
    perluan
    0.35
     Cite
    0.35
    Act Density 0.000%

    No Known Activations