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

    Neuronpedia

    INDEX
    Explanations

    maximizing differences in array

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mentions
    -0.09
    anch
    -0.09
    anchise
    -0.08
    huizen
    -0.07
     없는
    -0.07
     begleiten
    -0.07
     thankfully
    -0.07
     depreci
    -0.07
     finds
    -0.07
     совершен
    -0.07
    POSITIVE LOGITS
     alternating
    0.12
     arrangement
    0.10
    Arrangement
    0.10
     Arrangement
    0.10
     Altern
    0.09
    arr
    0.09
    alternate
    0.09
    .arr
    0.09
     alternate
    0.09
    _SEQUENCE
    0.09
    Act Density 0.020%

    No Known Activations