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

    Neuronpedia

    INDEX
    Explanations

    }

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wyn
    -0.07
    apan
    -0.07
    Descriptions
    -0.06
     immortal
    -0.06
    averse
    -0.06
     Kumar
    -0.06
     конструк
    -0.06
     ignorance
    -0.06
     Luc
    -0.06
     社
    -0.06
    POSITIVE LOGITS
    .makedirs
    0.07
    Subsystem
    0.06
     ''}↵
    0.06
    打
    0.06
     Warranty
    0.06
     murdering
    0.06
    fontWeight
    0.06
     επί
    0.06
    Ά
    0.06
     При
    0.06
    Act Density 0.002%

    No Known Activations