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

    Neuronpedia

    INDEX
    Explanations

    gt, code-related

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.06
     modelName
    -0.06
    -Q
    -0.06
    輪
    -0.06
    束
    -0.06
     dynasty
    -0.06
     dinh
    -0.06
     evolves
    -0.06
    perature
    -0.06
     �
    -0.05
    POSITIVE LOGITS
    .Place
    0.08
    vestment
    0.07
     Ty
    0.07
    ''↵
    0.07
     Philipp
    0.07
    .loadtxt
    0.07
    prices
    0.06
    (diff
    0.06
    าท
    0.06
    plat
    0.06
    Act Density 0.001%

    No Known Activations