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

    Neuronpedia

    INDEX
    Explanations

    human and image processing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    マータイヤ
    0.61
     Excise
    0.52
    yesters
    0.51
    átiles
    0.51
     Success
    0.50
    ကိုယ်
    0.50
     Part
    0.50
    見える
    0.48
     Espí
    0.48
     Fruits
    0.48
    POSITIVE LOGITS
    ﺒ
    0.43
     hab
    0.43
     дре
    0.42
     λεπ
    0.41
     ટુ
    0.41
    uyente
    0.40
    瞩
    0.39
     cance
    0.39
     ரே
    0.39
     blues
    0.39
    Act Density 0.000%

    No Known Activations