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

    Neuronpedia

    INDEX
    Explanations

    when timing or when

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Codec
    0.37
    ("'
    0.36
    னமாக
    0.35
    一种
    0.34
     grinder
    0.33
    èques
    0.33
    _{+}+
    0.32
     vượt
    0.32
     চলুন
    0.32
    Quality
    0.32
    POSITIVE LOGITS
     timing
    2.33
     Timing
    2.17
    Timing
    2.06
    timing
    2.03
     cuándo
    2.03
    何时
    2.00
    什么时候
    1.93
    タイミング
    1.91
     timings
    1.83
     WHEN
    1.78
    Act Density 0.047%

    No Known Activations