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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vul
    -0.07
     tempList
    -0.07
    CppType
    -0.07
    ymmetric
    -0.06
     typename
    -0.06
    �
    -0.06
    .Cons
    -0.06
    ゅ
    -0.06
    кав
    -0.06
     пож
    -0.06
    POSITIVE LOGITS
     LOGIN
    0.07
    (bar
    0.06
     img
    0.06
    ictor
    0.06
    .home
    0.06
    €�
    0.06
    dığı
    0.06
     sr
    0.06
    ¦
    0.06
     rept
    0.06
    Act Density 0.001%

    No Known Activations