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

    Neuronpedia

    INDEX
    Explanations

    INCLUDE

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Scene
    -0.08
     LINE
    -0.07
     certification
    -0.07
     hosted
    -0.07
    SetUp
    -0.07
    ч
    -0.06
    _python
    -0.06
    	pub
    -0.06
    orgot
    -0.06
     ricerca
    -0.06
    POSITIVE LOGITS
    ereum
    0.06
     Incredible
    0.06
     milestones
    0.06
    atern
    0.06
    wiąz
    0.06
     라이
    0.06
    ，最
    0.06
    <'
    0.06
    borough
    0.05
    asar
    0.05
    Act Density 0.001%

    No Known Activations