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

    Neuronpedia

    INDEX
    Explanations

    code and variables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sique
    -0.53
     Chwiliwch
    -0.51
     estekak
    -0.45
    komplet
    -0.44
     saja
    -0.43
    ngths
    -0.43
    fois
    -0.42
    ásra
    -0.42
     calldata
    -0.41
     Rectangle
    -0.41
    POSITIVE LOGITS
     its
    0.82
    Its
    0.81
     Its
    0.76
    :✨
    0.68
    它的
    0.68
     &___
    0.67
    ])){
    0.64
    its
    0.63
    XmlAccessorType
    0.61
    '])->
    0.61
    Act Density 0.036%

    No Known Activations