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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    있
    -0.08
     verdade
    -0.07
     culture
    -0.07
     ive
    -0.07
     dang
    -0.07
     gang
    -0.07
    Ģ
    -0.07
     VT
    -0.06
    עצמ
    -0.06
    ody
    -0.06
    POSITIVE LOGITS
     xếp
    0.08
     layered
    0.07
    散步
    0.07
    _FIELD
    0.07
     jede
    0.07
    .Fields
    0.07
     cuốn
    0.07
    ğun
    0.06
    女神
    0.06
     Bella
    0.06
    Act Density 0.035%

    No Known Activations