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

    Neuronpedia

    INDEX
    Explanations

    so

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Spir
    -0.08
     Hari
    -0.07
     prom
    -0.07
     consuming
    -0.07
     mon
    -0.07
    (common
    -0.07
    SIZE
    -0.06
    +.
    -0.06
     raw
    -0.06
    manent
    -0.06
    POSITIVE LOGITS
    ╞
    0.07
    ∨
    0.07
    maxLength
    0.07
     Solution
    0.06
    jest
    0.06
     seguir
    0.06
    >');↵↵
    0.06
    между
    0.06
    一樣
    0.06
     �
    0.06
    Act Density 0.011%

    No Known Activations