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

    Neuronpedia

    INDEX
    Explanations

    AM PM with time zones

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ELEASE
    0.99
    㧔
    0.98
    荕
    0.95
    垪
    0.91
     Faculté
    0.89
    㬶
    0.87
    .??.??"]
    0.85
    Attrib
    0.85
     મળ
    0.85
    鿌
    0.85
    POSITIVE LOGITS
     alongside
    0.92
     those
    0.79
     Cham
    0.79
     with
    0.79
    ,
    0.78
     without
    0.77
    ̂
    0.76
     were
    0.76
    ️
    0.72
     through
    0.72
    Act Density 0.002%

    No Known Activations