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

    Neuronpedia

    INDEX
    Explanations

    even

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     문서
    -0.07
    yal
    -0.07
     versatile
    -0.07
    41
    -0.07
     mundial
    -0.06
     dört
    -0.06
     tow
    -0.06
     通
    -0.06
     vers
    -0.06
     expects
    -0.06
    POSITIVE LOGITS
    ευ
    0.07
     Included
    0.07
     Barb
    0.06
    ा।↵↵
    0.06
    Refer
    0.06
    miştir
    0.06
    меж
    0.06
    CastException
    0.06
    called
    0.06
     ))}↵
    0.06
    Act Density 0.016%

    No Known Activations