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

    Neuronpedia

    INDEX
    Explanations

    statement directed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wretched
    0.48
     Boca
    0.47
     பிரசா
    0.47
    ˧
    0.47
     гля
    0.46
     drunken
    0.45
     ética
    0.45
     ไทย
    0.44
     Ελλάδα
    0.44
     К
    0.44
    POSITIVE LOGITS
    。
    0.60
    ially
    0.48
    อร์
    0.45
    良好
    0.45
     mogelijkheden
    0.44
     Caller
    0.42
     Controlled
    0.42
    shaped
    0.41
    towards
    0.41
    oble
    0.41
    Act Density 0.000%

    No Known Activations