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

    Neuronpedia

    INDEX
    Explanations

    arbitrary convention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    對
    0.65
    Е
    0.61
    З
    0.54
    Ç
    0.52
    M
    0.52
    B
    0.51
    G
    0.51
    Z
    0.51
    כו
    0.49
    ４
    0.49
    POSITIVE LOGITS
    textured
    0.49
    𝙩
    0.47
    newMessage
    0.47
    fler
    0.46
     lear
    0.46
     مرت
    0.45
     contoured
    0.45
     embodied
    0.44
     redefining
    0.44
     epit
    0.44
    Act Density 0.000%

    No Known Activations