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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WELCOME
    -0.08
     finit
    -0.08
     السود
    -0.08
    、副
    -0.08
     والتح
    -0.08
     tantas
    -0.08
     faint
    -0.07
     ارتفاع
    -0.07
     Moro
    -0.07
     Sop
    -0.07
    POSITIVE LOGITS
     cuisine
    0.08
     ctxt
    0.07
     Heavy
    0.07
     എന്നിവ
    0.07
    dbh
    0.07
    ,$
    0.07
     Chad
    0.07
    sex
    0.07
    _CAM
    0.07
    "ש
    0.07
    Act Density 0.080%

    No Known Activations