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

    Neuronpedia

    INDEX
    Explanations

    descending

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     candidates
    -0.07
     lantern
    -0.07
     demon
    -0.06
     vr
    -0.06
    isp
    -0.06
    Stuff
    -0.06
    Republicans
    -0.06
     FRIEND
    -0.06
    主演
    -0.06
    ields
    -0.06
    POSITIVE LOGITS
    .rename
    0.08
    .TextBox
    0.07
    _bool
    0.07
     och
    0.07
    ("
    0.07
    -enable
    0.07
    ："
    0.07
    .multiply
    0.07
    非常高
    0.07
    natural
    0.07
    Act Density 0.010%

    No Known Activations