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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eree
    -0.07
    Wide
    -0.06
     میدان
    -0.06
    ट
    -0.06
     tomato
    -0.06
    quake
    -0.06
    ены
    -0.06
    Spider
    -0.06
    Extra
    -0.06
     Shia
    -0.06
    POSITIVE LOGITS
     baj
    0.07
     '*',
    0.06
     přiv
    0.06
    �
    0.06
    .InnerText
    0.06
     bh
    0.06
     hes
    0.06
    ,’’
    0.06
     use
    0.06
    .Base
    0.06
    Act Density 0.021%

    No Known Activations