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

    Neuronpedia

    INDEX
    Explanations

    a little

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    나
    1.14
     allowing
    1.13
    getting
    1.12
     Gefühl
    1.06
     zusamm
    1.05
     inability
    1.03
     proced
    1.03
    ைகளுக்கு
    1.02
    াদের
    1.02
     Allowing
    1.00
    POSITIVE LOGITS
     ])
    1.30
     }}{
    1.30
     crap
    1.27
    }{\
    1.27
     ถาม
    1.26
    ysts
    1.26
    ideos
    1.25
     вниз
    1.23
    繹
    1.23
    issati
    1.23
    Act Density 0.274%

    No Known Activations