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

    Neuronpedia

    INDEX
    Explanations

    p-value significance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     :+:
    0.43
    窨
    0.42
    దారు
    0.39
    䅞
    0.38
    㵴
    0.38
    nemidophorus
    0.37
    ఇ
    0.37
     свойства
    0.37
     ஹை
    0.37
    आ
    0.36
    POSITIVE LOGITS
     p
    0.99
     significance
    0.81
     Significance
    0.75
     P
    0.73
     value
    0.68
     values
    0.63
    value
    0.59
     insignificant
    0.55
     값
    0.52
     nilai
    0.52
    Act Density 0.005%

    No Known Activations