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

    Neuronpedia

    INDEX
    Explanations

    units of time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Figura
    0.41
    :
    0.39
    ,
    0.38
    ),
    0.38
     the
    0.37
     it
    0.36
     จํา
    0.36
    )
    0.36
                              
    0.35
     반드시
    0.35
    POSITIVE LOGITS
     vuoi
    0.48
     días
    0.45
    minutes
    0.44
    tiktok
    0.44
    tahun
    0.44
    time
    0.42
    uzzy
    0.42
    èrement
    0.42
     அரசு
    0.42
    D
    0.42
    Act Density 0.024%

    No Known Activations