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

    Neuronpedia

    INDEX
    Explanations

    Code/Mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <Boolean
    -0.08
     통해
    -0.07
    ","",
    -0.07
     Moderator
    -0.06
    邦
    -0.06
     lạnh
    -0.06
     �
    -0.06
    액
    -0.06
     FactoryBot
    -0.06
    ，加
    -0.06
    POSITIVE LOGITS
     TEN
    0.07
     dine
    0.07
    mentation
    0.06
    _state
    0.06
     ListItem
    0.06
     Soup
    0.06
     sustain
    0.06
    .SelectedValue
    0.06
     nn
    0.06
     القي
    0.06
    Act Density 0.013%

    No Known Activations