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

    Neuronpedia

    INDEX
    Explanations

    circle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     (?
    -0.09
    验证
    -0.08
     Verification
    -0.08
     "?
    -0.08
     verificar
    -0.08
     ?
    -0.07
    ?)
    -0.07
    .Text
    -0.07
     verific
    -0.07
     zweimal
    -0.07
    POSITIVE LOGITS
    positive
    0.10
     positive
    0.10
     सकारात्मक
    0.10
     tendency
    0.09
     pozitiv
    0.08
     مثبت
    0.08
     positif
    0.08
    negative
    0.08
     southeast
    0.08
     positi
    0.08
    Act Density 0.085%

    No Known Activations