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

    Neuronpedia

    INDEX
    Explanations

    Gos

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ruits
    -0.06
     Recorded
    -0.06
     masked
    -0.06
     Parad
    -0.06
     historic
    -0.06
     Alberta
    -0.06
     hwnd
    -0.06
     indie
    -0.06
     books
    -0.06
    065
    -0.06
    POSITIVE LOGITS
     Sher
    0.07
    _NET
    0.07
     حالة
    0.06
    alendar
    0.06
     ausge
    0.06
    ég
    0.06
     REGARD
    0.06
    �
    0.06
     coquine
    0.06
    _g
    0.06
    Act Density 0.004%

    No Known Activations