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

    Neuronpedia

    INDEX
    Explanations

    return statement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.46
     sophisticated
    0.46
     burrow
    0.43
     treacherous
    0.39
    Danh
    0.39
     scale
    0.39
     unforgettable
    0.39
     ambitious
    0.38
     luc
    0.38
     unsettling
    0.38
    POSITIVE LOGITS
    kits
    0.54
    었다
    0.48
    īs
    0.47
    տ
    0.47
    𝐢
    0.47
    кі
    0.47
    reviewer
    0.46
    師
    0.46
    er
    0.45
    ரி
    0.45
    Act Density 0.001%

    No Known Activations