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

    Neuronpedia

    INDEX
    Explanations

    core and fundamental values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ก
    0.59
    क
    0.55
     dată
    0.52
     moyenne
    0.52
     getImage
    0.51
     término
    0.50
     ระ
    0.49
    ă
    0.49
     déjeuner
    0.48
    k
    0.47
    POSITIVE LOGITS
     Values
    0.68
    V
    0.64
    Z
    0.58
    Values
    0.55
     values
    0.53
    را
    0.52
     Blick
    0.52
    iyoruz
    0.51
    мой
    0.49
    I
    0.49
    Act Density 0.005%

    No Known Activations