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

    Neuronpedia

    INDEX
    Explanations

    m

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _IOC
    -0.07
     kot
    -0.06
     Liga
    -0.06
    ETYPE
    -0.06
    	dest
    -0.06
     dnů
    -0.06
     민주
    -0.06
     jobs
    -0.06
    /pub
    -0.06
    jack
    -0.06
    POSITIVE LOGITS
    decision
    0.07
    Invoice
    0.06
     Report
    0.06
     logically
    0.06
    ugeot
    0.06
     haciendo
    0.06
    час
    0.06
     respectfully
    0.06
    گیر
    0.06
    Coverage
    0.06
    Act Density 0.000%

    No Known Activations