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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    应
    -0.07
    ))));↵
    -0.07
     م
    -0.06
     Devon
    -0.06
    Australia
    -0.06
    CSR
    -0.06
    	↵	↵	↵
    -0.06
    ，你
    -0.06
     CFR
    -0.06
     erf
    -0.06
    POSITIVE LOGITS
    Currency
    0.07
    /h
    0.06
     Greeks
    0.06
    /basic
    0.06
     footnote
    0.06
     EXEC
    0.06
     bend
    0.06
    LineWidth
    0.06
     scipy
    0.06
     ettir
    0.06
    Act Density 0.003%

    No Known Activations