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

    Neuronpedia

    INDEX
    Explanations

    thinking or supposing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ეფ
    0.40
    ುತ್ತವೆ
    0.39
    ясплат
    0.38
     সার্চ
    0.36
    ຕາມ
    0.36
    ௦
    0.36
     кое
    0.35
    シン
    0.35
     практически
    0.35
    ᵘ
    0.34
    POSITIVE LOGITS
    以為
    0.64
    以为
    0.63
     surely
    0.55
     maybe
    0.55
     বুঝি
    0.52
     Surely
    0.51
    maybe
    0.48
    Surely
    0.46
     Maybe
    0.45
    Maybe
    0.44
    Act Density 0.007%

    No Known Activations