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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ಹೊಂದ
    -0.07
    -0.07
    മുള്ള
    -0.07
     रखने
    -0.07
    ierter
    -0.07
    pd
    -0.07
     ಬಳಸ
    -0.07
     Avery
    -0.07
     sorprender
    -0.07
    commande
    -0.07
    POSITIVE LOGITS
     CONTRIBUT
    0.09
     diễn
    0.08
     mì
    0.08
     fought
    0.08
     riots
    0.08
    ּ
    0.08
     beaches
    0.08
    柄
    0.08
     Belfast
    0.08
     باس
    0.08
    Act Density 0.005%
    No Known Activations