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

    Neuronpedia

    INDEX
    Explanations

    cost

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -1.48
    ^(@)
    -1.17
    NUMX
    -1.01
    writeFieldEnd
    -0.99
    ValueStyle
    -0.96
     defaultstate
    -0.95
    GraphicsUnit
    -0.92
    WriteTagHelper
    -0.91
    setViewportView
    -0.90
    ."]
    -0.88
    POSITIVE LOGITS
     
    0.50
    I
    0.50
    ul
    0.47
    h
    0.46
    ot
    0.45
    ol
    0.44
    E
    0.44
    ir
    0.43
    P
    0.43
    is
    0.43
    Act Density 0.923%

    No Known Activations