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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Lifetime
    -0.07
     Mat
    -0.07
     go
    -0.07
    _objects
    -0.07
     apprentices
    -0.06
     herpes
    -0.06
     served
    -0.06
     mat
    -0.06
     serves
    -0.06
                    
    -0.06
    POSITIVE LOGITS
    opp
    0.07
    ียม
    0.06
    мож
    0.06
    *******************************************************************************/↵
    0.06
     hue
    0.06
    vocab
    0.06
    uggy
    0.06
     характеристики
    0.06
     Zucker
    0.06
    icago
    0.06
    Act Density 0.000%

    No Known Activations