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

    Neuronpedia

    INDEX
    Explanations

    to of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     remarks
    -0.07
    Therefore
    -0.07
    ometers
    -0.06
    IBLE
    -0.06
    qtt
    -0.06
     first
    -0.06
    cheduler
    -0.06
    itation
    -0.06
    itizen
    -0.06
    Anyone
    -0.06
    POSITIVE LOGITS
     WaitFor
    0.07
    子の
    0.07
     onAnimation
    0.06
     sacrific
    0.06
    .Load
    0.06
     of
    0.06
     ώρα
    0.06
    _UNIT
    0.06
    .Xtra
    0.06
    .BOLD
    0.06
    Act Density 0.276%

    No Known Activations