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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Foot
    -0.07
    undan
    -0.06
    ,C
    -0.06
    policy
    -0.06
    ารย
    -0.06
    cards
    -0.06
    -stat
    -0.06
    Speaking
    -0.06
    ('@
    -0.06
    /docs
    -0.06
    POSITIVE LOGITS
     तरफ
    0.08
     η
    0.07
    丶
    0.06
    getWidth
    0.06
     REST
    0.06
     szy
    0.06
    UILTIN
    0.06
     �
    0.06
    리
    0.06
     zou
    0.06
    Act Density 0.015%

    No Known Activations