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

    Neuronpedia

    INDEX
    Explanations

    refers to Group B

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    í
    0.66
    î
    0.50
    є
    0.46
    {
    0.46
    ğ
    0.46
     mé
    0.45
     ตำ
    0.44
    ý
    0.43
     cảnh
    0.43
    dures
    0.42
    POSITIVE LOGITS
     undercut
    0.45
    挛
    0.43
     McL
    0.43
    ximately
    0.42
    鰹
    0.42
    plaats
    0.41
    在使用
    0.41
    VL
    0.40
    ledged
    0.40
     methylene
    0.40
    Act Density 0.000%

    No Known Activations