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

    Neuronpedia

    INDEX
    Explanations

    list items ending in punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಋ
    0.46
     सुष
    0.45
    thiaz
    0.45
    ᱓
    0.45
     леген
    0.44
    🌥
    0.44
     преди
    0.43
     ಹೃ
    0.43
     предше
    0.43
    合理的
    0.43
    POSITIVE LOGITS
    FOV
    0.55
     this
    0.54
     can
    0.54
    f
    0.54
    ing
    0.51
    ed
    0.51
    ee
    0.50
     scelta
    0.48
     mic
    0.48
    a
    0.48
    Act Density 0.000%

    No Known Activations