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

    Neuronpedia

    INDEX
    Explanations

    on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ″
    1.05
    ে
    1.03
    Error
    0.96
    letzt
    0.96
    ми
    0.95
    ]&
    0.90
    𝓵
    0.87
    ःख
    0.86
    leştir
    0.86
    ने
    0.84
    POSITIVE LOGITS
     behalf
    1.53
     occasion
    1.12
    िक्रमा
    1.10
     základě
    1.09
     протяжении
    1.07
     horseback
    1.05
     основе
    1.03
    slaught
    1.02
     مشتمل
    1.01
    nå
    0.97
    Act Density 0.235%

    No Known Activations