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

    Neuronpedia

    INDEX
    Explanations

    divisions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bandung
    -0.09
     mediados
    -0.09
     tecnico
    -0.08
     Assess
    -0.08
    НР
    -0.08
    .tie
    -0.08
     วิเคราะห์
    -0.08
     Técnico
    -0.08
    	action
    -0.08
     Zentral
    -0.08
    POSITIVE LOGITS
     punctuation
    0.10
     divides
    0.10
     separated
    0.09
     punct
    0.08
     structure
    0.08
    划
    0.08
     divisions
    0.08
     deline
    0.08
     makes
    0.08
     neatly
    0.08
    Act Density 0.024%

    No Known Activations