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

    Neuronpedia

    INDEX
    Explanations

    Website policies and disclaimers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     provisioning
    -0.07
     Foley
    -0.07
     stu
    -0.06
     Lv
    -0.06
    004
    -0.06
     Giáo
    -0.06
     auxiliary
    -0.06
    setWidth
    -0.06
    _phi
    -0.06
    parameters
    -0.06
    POSITIVE LOGITS
    -Out
    0.07
     замов
    0.06
    paragus
    0.06
     sedan
    0.06
    emetery
    0.06
     Appears
    0.06
     불
    0.06
     outspoken
    0.06
     इक
    0.06
     demo
    0.06
    Act Density 0.016%

    No Known Activations