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

    Neuronpedia

    INDEX
    Explanations

    "

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ник
    -0.06
    Seven
    -0.06
     iw
    -0.06
    Aside
    -0.06
    Pagination
    -0.06
    intelligence
    -0.06
    stress
    -0.06
    (res
    -0.06
    irteen
    -0.06
     selling
    -0.06
    POSITIVE LOGITS
     disse
    0.07
     เท
    0.06
    ظˆ
    0.06
     Kitt
    0.06
     Charleston
    0.06
     عفش
    0.06
    /kernel
    0.06
     Serena
    0.06
    utsche
    0.06
     Emm
    0.06
    Act Density 0.002%

    No Known Activations