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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ampl
    -0.07
    ��
    -0.07
    /*@
    -0.06
    porate
    -0.06
     her
    -0.06
     publish
    -0.06
     partic
    -0.06
     pregn
    -0.06
    plication
    -0.06
     intrinsic
    -0.06
    POSITIVE LOGITS
     ['/
    0.07
     Result
    0.06
    (jLabel
    0.06
    )";↵↵
    0.06
     athleticism
    0.06
    ازات
    0.06
    Eight
    0.06
    。これ
    0.06
     Es
    0.06
     úprav
    0.06
    Act Density 0.000%

    No Known Activations