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

    Neuronpedia

    INDEX
    Explanations

    messages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ungkin
    -0.07
     alumnos
    -0.06
    파
    -0.06
     anche
    -0.06
     benz
    -0.06
    ENCIES
    -0.06
     vér
    -0.06
     adalah
    -0.06
     nuis
    -0.06
     dahil
    -0.06
    POSITIVE LOGITS
    plug
    0.07
    lon
    0.07
    <TreeNode
    0.06
     "",
    0.06
    063
    0.06
    muz
    0.06
     
↵
↵
    0.06
    ableView
    0.06
     exploration
    0.06
    【
    0.06
    Act Density 0.030%

    No Known Activations