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

    Neuronpedia

    INDEX
    Explanations

    opinion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .drag
    -0.07
    뺴
    -0.07
     &&
    -0.07
    把你
    -0.07
     בשנים
    -0.07
     sous
    -0.06
    nda
    -0.06
    呕吐
    -0.06
     drag
    -0.06
     '.')
    -0.06
    POSITIVE LOGITS
     üniversite
    0.07
    ຈ
    0.07
     Rican
    0.07
    cheme
    0.07
     Americ
    0.07
    -region
    0.07
    鄘
    0.07
    {})
    0.07
    efficient
    0.07
    mention
    0.07
    Act Density 0.001%

    No Known Activations