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

    Neuronpedia

    INDEX
    Explanations

    geometry construction problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .dropout
    -0.08
    tbody
    -0.07
     EI
    -0.07
     aggressively
    -0.07
     turquoise
    -0.07
    67
    -0.07
    879
    -0.07
    378
    -0.07
     aggressive
    -0.07
     Earnings
    -0.07
    POSITIVE LOGITS
     desider
    0.11
     previamente
    0.10
     имеется
    0.09
     مسب
    0.09
    blico
    0.09
     تعیین
    0.09
     peteĩ
    0.09
     predetermined
    0.09
     располож
    0.09
     Auftrag
    0.09
    Act Density 0.042%

    No Known Activations