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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Black
    -0.08
    (sign
    -0.08
     repeal
    -0.08
    Messaging
    -0.08
    Breakpoint
    -0.08
    Opponent
    -0.07
     جمعية
    -0.07
     plage
    -0.07
     Mustang
    -0.07
     partisan
    -0.07
    POSITIVE LOGITS
    _dimensions
    0.13
     Dimensions
    0.13
     dimensions
    0.12
    Dimensions
    0.11
     الثلاث
    0.11
    _dims
    0.11
     xyz
    0.11
     three
    0.11
     dimens
    0.10
     dimensiones
    0.10
    Act Density 0.035%

    No Known Activations