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

    Neuronpedia

    INDEX
    Explanations

    safety of responses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nathan
    -0.10
    arity
    -0.10
    SION
    -0.09
     dra
    -0.09
     flows
    -0.09
    COM
    -0.09
    acho
    -0.08
    loggedIn
    -0.08
     Dra
    -0.08
     ho
    -0.08
    POSITIVE LOGITS
    iani
    0.10
     productivity
    0.10
    AreaView
    0.09
     ï¼ľ
    0.09
    éli
    0.09
    PIO
    0.09
    AML
    0.09
    evin
    0.09
    ledi
    0.09
    IVO
    0.09
    Act Density 0.060%

    No Known Activations