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

    Neuronpedia

    INDEX
    Explanations

    ab

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dincer
    0.54
    नेल
    0.41
     เง
    0.41
     pretože
    0.41
     protože
    0.41
    RuL
    0.40
    নায়
    0.40
     DSF
    0.40
    ဃ
    0.39
    ppes
    0.39
    POSITIVE LOGITS
     English
    0.40
     parks
    0.38
     University
    0.37
     english
    0.37
     primary
    0.36
     decades
    0.36
     Park
    0.36
     Roma
    0.36
     Plaza
    0.36
     family
    0.35
    Act Density 0.001%

    No Known Activations