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

    Neuronpedia

    INDEX
    Explanations

    names and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     abutting
    0.46
     THERE
    0.43
     needed
    0.43
     ನಿಮಗೆ
    0.42
     essayé
    0.42
     circost
    0.41
     singular
    0.41
     dowol
    0.41
     modalidad
    0.40
    ্সের
    0.40
    POSITIVE LOGITS
    男性
    0.40
    贤
    0.39
    Stephen
    0.39
     administratif
    0.38
     Stephen
    0.38
     Administrative
    0.38
    axiom
    0.38
    𖥔
    0.38
    ፐ
    0.38
     Jahn
    0.38
    Act Density 0.000%

    No Known Activations