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

    Neuronpedia

    INDEX
    Explanations

    questions seeking advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stets
    0.44
     Tuttavia
    0.40
    \!\
    0.38
     tendrás
    0.37
     செல்லும்
    0.37
     Estamos
    0.36
     Однако
    0.36
     ہماری
    0.36
     نتیجہ
    0.35
     Ancak
    0.35
    POSITIVE LOGITS
    ?</
    0.67
    ？
    0.65
    ？）
    0.64
     mogę
    0.62
     myself
    0.61
    ？」
    0.61
    ？”
    0.60
     posso
    0.59
    私が
    0.59
    ?
    0.59
    Act Density 0.051%

    No Known Activations