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

    Neuronpedia

    INDEX
    Explanations

    Employee engagement and emotions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .alert
    -0.09
    Todd
    -0.08
    日下午
    -0.08
    /full
    -0.08
    ещения
    -0.08
    Tony
    -0.08
    (button
    -0.08
    .analysis
    -0.08
     volledige
    -0.08
     정도
    -0.08
    POSITIVE LOGITS
     the
    0.07
     terms
    0.07
     Sark
    0.07
     സ്ഥാപന
    0.07
     ಯ
    0.07
     Claim
    0.07
     claims
    0.06
     werkgever
    0.06
     spatial
    0.06
     Include
    0.06
    Act Density 0.001%

    No Known Activations