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

    Neuronpedia

    INDEX
    Explanations

    UI elements and programming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disappointing
    0.42
     disappointment
    0.42
    usional
    0.41
    ubishi
    0.40
     फिसल
    0.40
    imilar
    0.40
     রংপুর
    0.40
    uttgart
    0.39
     burgundy
    0.39
     motorbike
    0.38
    POSITIVE LOGITS
     decoder
    0.38
     Decoder
    0.37
     modulated
    0.36
     задач
    0.36
    KV
    0.35
     wrapped
    0.35
    Dropdown
    0.34
     linestyle
    0.34
     riform
    0.34
     Valuation
    0.34
    Act Density 0.001%

    No Known Activations