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

    Neuronpedia

    INDEX
    Explanations

    gag

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clarify
    -0.07
    :true
    -0.07
    elda
    -0.06
    Archivo
    -0.06
     obstacle
    -0.06
    emet
    -0.06
    IFI
    -0.06
    .syntax
    -0.06
    Fx
    -0.06
     background
    -0.06
    POSITIVE LOGITS
     Sabha
    0.07
    นาง
    0.06
    _shared
    0.06
     cocoa
    0.06
    (tuple
    0.06
     Hoover
    0.06
    签字
    0.06
     enclosure
    0.06
    קס
    0.06
     NSLayoutConstraint
    0.06
    Act Density 0.001%

    No Known Activations