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

    Neuronpedia

    INDEX
    Explanations

    common things, typical things

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    omock
    -0.60
     is
    -0.59
     was
    -0.53
     demografica
    -0.53
     has
    -0.51
    -------------</
    -0.48
    AndEndTag
    -0.46
    styleUrls
    -0.46
    الحياه
    -0.46
    さが
    -0.46
    POSITIVE LOGITS
     procedure
    0.57
     calculation
    0.57
    cshtml
    0.57
    y
    0.55
     factors
    0.55
     proportion
    0.55
     purpose
    0.54
     fhew
    0.54
     individuals
    0.54
     فريبيس
    0.53
    Act Density 0.005%

    No Known Activations