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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _WR
    -0.08
     slun
    -0.07
    Leading
    -0.07
     predatory
    -0.07
    elling
    -0.07
    avers
    -0.06
    Messaging
    -0.06
    	X
    -0.06
    Playable
    -0.06
     indoors
    -0.06
    POSITIVE LOGITS
    .toolStripSeparator
    0.07
    -picker
    0.07
    equal
    0.06
    =<
    0.06
    ="<<
    0.06
     Oak
    0.06
    /catalog
    0.06
    /current
    0.06
     distinctions
    0.06
    _BRANCH
    0.06
    Act Density 0.324%

    No Known Activations