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

    Neuronpedia

    INDEX
    Explanations

    7

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pob
    -0.07
    ezi
    -0.06
    urer
    -0.06
    (server
    -0.06
    ких
    -0.06
     bowel
    -0.06
    777
    -0.06
    коз
    -0.06
    tains
    -0.06
    τήσεις
    -0.05
    POSITIVE LOGITS
     Resolution
    0.07
    sı
    0.06
     그의
    0.06
     Mex
    0.06
    一直
    0.06
    Af
    0.06
    Unsafe
    0.06
     formatted
    0.06
    긴
    0.06
    geom
    0.06
    Act Density 0.001%

    No Known Activations