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

    Neuronpedia

    INDEX
    Explanations

    someone

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    述
    -0.07
    sets
    -0.07
    set
    -0.07
    -",
    -0.06
     py
    -0.06
     yapan
    -0.06
    iever
    -0.06
     denim
    -0.06
    _students
    -0.06
     slows
    -0.06
    POSITIVE LOGITS
    ilih
    0.06
     rampage
    0.06
     esper
    0.06
    Invoker
    0.06
    cele
    0.06
    аш
    0.06
     CONTEXT
    0.06
    анс
    0.06
     неиз
    0.06
     raping
    0.06
    Act Density 0.000%

    No Known Activations