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

    Neuronpedia

    INDEX
    Explanations

    appeal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stamps
    -0.07
    _bootstrap
    -0.07
    .Exp
    -0.07
    .Index
    -0.06
    ça
    -0.06
    Load
    -0.06
    _idx
    -0.06
     securities
    -0.06
     Fly
    -0.06
    SOR
    -0.06
    POSITIVE LOGITS
     Knights
    0.07
     دولار
    0.06
     вер
    0.06
    crypto
    0.06
     empleado
    0.06
     ordained
    0.06
    QRSTUVWXYZ
    0.06
     offending
    0.06
    /',↵
    0.06
    허
    0.06
    Act Density 0.042%

    No Known Activations