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

    Neuronpedia

    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "..\..\
    -0.63
     "..\..\..\
    -0.55
    ValueStyle
    -0.52
    rungsseite
    -0.51
    OrBuilder
    -0.50
    NUMX
    -0.50
    DJANGO
    -0.44
     propellant
    -0.44
     whistle
    -0.43
    JspWriter
    -0.43
    POSITIVE LOGITS
    phazard
    0.59
     بيها
    0.58
     처리
    0.56
     Boven
    0.56
    Kontrola
    0.56
    qtype
    0.54
     puissent
    0.54
    ollett
    0.52
    Xna
    0.51
     IBOutlet
    0.51
    Act Density 0.007%

    No Known Activations