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

    Neuronpedia

    INDEX
    Explanations

    ial

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    student
    -0.07
     dense
    -0.07
    userInfo
    -0.06
    elerini
    -0.06
     window
    -0.06
     bake
    -0.06
     cloak
    -0.06
    情况
    -0.05
     interess
    -0.05
     sera
    -0.05
    POSITIVE LOGITS
    論
    0.07
    paragraph
    0.07
     انتخاب
    0.06
    ICIAL
    0.06
     Э
    0.06
     질
    0.06
    کیل
    0.06
     editorial
    0.06
     Sanity
    0.06
    _bs
    0.06
    Act Density 0.001%

    No Known Activations