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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ITER
    -0.07
     intercepted
    -0.06
     linen
    -0.06
     सम
    -0.06
    lament
    -0.06
    -debug
    -0.06
    Essay
    -0.06
    .／
    -0.06
     Amen
    -0.06
     worn
    -0.06
    POSITIVE LOGITS
    Go
    0.08
     Go
    0.07
     tảng
    0.06
    .requires
    0.06
     comprises
    0.06
     khỏ
    0.06
    уса
    0.06
     php
    0.06
    roller
    0.06
     Пер
    0.06
    Act Density 0.005%

    No Known Activations