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

    Neuronpedia

    INDEX
    Explanations

    alphabet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     uploading
    -0.07
    .GetProperty
    -0.07
     frail
    -0.06
    .tail
    -0.06
     Particle
    -0.06
    asma
    -0.06
     Pir
    -0.06
     microseconds
    -0.06
     wield
    -0.06
    olecules
    -0.06
    POSITIVE LOGITS
    (dat
    0.07
    лоп
    0.07
    alloc
    0.07
    unched
    0.07
     numel
    0.06
     Searching
    0.06
    omba
    0.06
    0.06
    REFIX
    0.06
    paper
    0.06
    Act Density 0.003%

    No Known Activations