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

    Neuronpedia

    INDEX
    Explanations

    G

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .phoneNumber
    -0.07
     merkez
    -0.06
     Domestic
    -0.06
     Ku
    -0.06
    (float
    -0.06
    twitter
    -0.06
     CL
    -0.06
     مركز
    -0.06
    ::{↵
    -0.06
    %).
    -0.06
    POSITIVE LOGITS
     میلادی
    0.07
     offset
    0.06
     Joint
    0.06
    .damage
    0.06
     GetCurrent
    0.06
    ٔ
    0.06
     gard
    0.06
     간
    0.06
    اکم
    0.06
    �
    0.06
    Act Density 0.010%

    No Known Activations