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

    Neuronpedia

    INDEX
    Explanations

    non-negotiable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     RasterModelGrid
    0.41
     দত্ত
    0.41
    isPrime
    0.39
    fileTool
    0.39
     Urine
    0.38
    🌇
    0.38
    ḧ
    0.38
    ಿಸಿಕೊಂಡ
    0.38
     উপকার
    0.37
    தியின்
    0.37
    POSITIVE LOGITS
     negotiation
    3.95
     negotiations
    3.94
     negotiating
    3.73
    Negoti
    3.69
    negoti
    3.66
     negotiate
    3.63
     Negotiations
    3.59
     Negotiation
    3.50
     negoti
    3.45
     negoci
    3.41
    Act Density 0.035%

    No Known Activations