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

    Neuronpedia

    INDEX
    Explanations

    to be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ya
    -0.07
    -distance
    -0.07
    _growth
    -0.06
     transformed
    -0.06
    Ya
    -0.06
     lexical
    -0.06
     La
    -0.06
    (inter
    -0.06
    GetMapping
    -0.06
     presents
    -0.06
    POSITIVE LOGITS
    간
    0.06
     detail
    0.06
    .Reverse
    0.06
    SignUp
    0.06
     général
    0.06
     szcz
    0.06
     ephem
    0.06
    วม
    0.06
     peu
    0.06
     munch
    0.06
    Act Density 0.045%

    No Known Activations