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

    Neuronpedia

    INDEX
    Explanations

    markdown formatting and structured text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    偈
    0.25
     covariance
    0.25
     viscosity
    0.25
     वनस्पती
    0.24
     subtree
    0.24
    டியான
    0.24
     yoj
    0.23
     detract
    0.23
     इट्स
    0.23
     Its
    0.22
    POSITIVE LOGITS
    <h2>
    0.52
    <h3>
    0.49
    <h1>
    0.48
    ##
    0.48
    ###
    0.45
    <h4>
    0.39
     ###
    0.38
     ##
    0.37
    **
    0.36
     **
    0.33
    Act Density 0.092%

    No Known Activations