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

    Neuronpedia

    INDEX
    Explanations

    Code or scientific notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     licens
    -0.07
     neighbours
    -0.06
     Picasso
    -0.06
     violation
    -0.06
    、それ
    -0.06
     przypad
    -0.06
    анти
    -0.06
    ナル
    -0.06
    **
    -0.06
     rejection
    -0.06
    POSITIVE LOGITS
     setObject
    0.07
     setC
    0.07
    fontWeight
    0.07
    エ
    0.07
    ider
    0.06
     (↵
    0.06
     NN
    0.06
     '/',↵
    0.06
    _NODES
    0.06
    vere
    0.06
    Act Density 0.052%

    No Known Activations