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

    Neuronpedia

    INDEX
    Explanations

    months and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Between
    0.46
    Feb
    0.42
     Interim
    0.42
    今年的
    0.39
     totalité
    0.38
     DURING
    0.38
     Between
    0.38
     további
    0.38
     Foire
    0.37
     গতকাল
    0.37
    POSITIVE LOGITS
    iaz
    0.36
    КС
    0.35
    ahl
    0.34
     averted
    0.33
    azen
    0.33
    HTT
    0.33
    的影响
    0.33
     tabb
    0.32
    she
    0.32
    }--\
    0.32
    Act Density 0.019%

    No Known Activations