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

    Neuronpedia

    INDEX
    Explanations

    issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.65
    NameInMap
    -0.63
    
    -0.62
     TextAppearance
    -0.61
     مرئيه
    -0.61
     saites
    -0.60
     fhew
    -0.60
     ✭✭
    -0.59
    ArrowToggle
    -0.59
     BOND
    -0.58
    POSITIVE LOGITS
     related
    0.64
     pertaining
    0.63
     affecting
    0.61
     relating
    0.59
     facing
    0.54
    related
    0.51
     imp
    0.50
     impacting
    0.48
     faced
    0.47
    الإنجليزية
    0.47
    Act Density 0.002%

    No Known Activations