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

    Neuronpedia

    INDEX
    Explanations

    header

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ฝ
    -0.08
    ientes
    -0.07
    🎇
    -0.07
     Pist
    -0.07
    ụ
    -0.06
    fest
    -0.06
    🧑
    -0.06
    ʈ
    -0.06
    ะ
    -0.06
    ន
    -0.06
    POSITIVE LOGITS
     drib
    0.07
     ENTRY
    0.07
    Multip
    0.07
    .image
    0.07
    (ip
    0.07
     KO
    0.07
    的地步
    0.07
     #
↵
    0.07
     oran
    0.07
     singleton
    0.07
    Act Density 0.002%

    No Known Activations