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

    Neuronpedia

    INDEX
    Explanations

    visual appeal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝜌
    1.02
    𓏧
    1.00
    bildung
    0.99
     giãn
    0.98
     phonons
    0.96
     ángulos
    0.96
    ℝ
    0.96
     hypersurfaces
    0.96
     آئینے
    0.96
    𝜎
    0.96
    POSITIVE LOGITS
    '
    1.01
    0.88
    GA
    0.83
    '.
    0.82
    .
    0.81
    ↵↵
    0.79
    0.75
    WE
    0.75
    .'
    0.72
    eg
    0.71
    Act Density 0.000%

    No Known Activations