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

    Neuronpedia

    INDEX
    Explanations

    greetings and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FL
    0.42
    j
    0.40
     prey
    0.40
    드의
    0.39
     Saddle
    0.39
    think
    0.38
    whale
    0.38
     रोटी
    0.38
    fl
    0.38
    jl
    0.38
    POSITIVE LOGITS
    ilis
    0.43
    ıdır
    0.40
    ることが
    0.40
    oglas
    0.38
     пу
    0.38
    itando
    0.38
    ernos
    0.38
    塔尔
    0.38
     иде
    0.38
    íticas
    0.38
    Act Density 0.000%

    No Known Activations