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

    Neuronpedia

    INDEX
    Explanations

    customer recently discovered

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    се
    0.49
    ей
    0.45
    ра
    0.41
    ре
    0.41
    с
    0.41
    ри
    0.40
    реги
    0.40
    ách
    0.40
    v
    0.39
    op
    0.39
    POSITIVE LOGITS
    Ꮰ
    0.54
    梠
    0.51
    𝑰
    0.50
     IQR
    0.50
     таке
    0.49
    𝗘
    0.48
     Į
    0.48
     Eqs
    0.47
    ᒎ
    0.47
    Kalau
    0.46
    Act Density 0.001%

    No Known Activations