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

    Neuronpedia

    INDEX
    Explanations

    31

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Duncan
    -0.07
    Nullable
    -0.07
    ạm
    -0.07
     Craw
    -0.07
    458
    -0.06
    mount
    -0.06
    shape
    -0.06
    602
    -0.06
    чу
    -0.06
    odb
    -0.06
    POSITIVE LOGITS
    ظم
    0.08
    Knowledge
    0.07
    ΙΚ
    0.07
    31
    0.07
    .head
    0.07
    Archive
    0.06
    (eventName
    0.06
    olina
    0.06
    HL
    0.06
     nek
    0.06
    Act Density 0.009%

    No Known Activations