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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HD
    -0.07
    对他们
    -0.07
    _patch
    -0.07
    Aug
    -0.06
    元旦
    -0.06
     NEED
    -0.06
     Bas
    -0.06
    _mob
    -0.06
    布置
    -0.06
    香港
    -0.06
    POSITIVE LOGITS
    isma
    0.08
    سعر
    0.07
    FormatException
    0.07
    써
    0.07
     стала
    0.07
     (($
    0.07
     yOffset
    0.07
    itational
    0.07
    _er
    0.07
     Priority
    0.07
    Act Density 0.008%

    No Known Activations