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

    Neuronpedia

    INDEX
    Explanations

    ethics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PIO
    -0.07
     obce
    -0.07
    >";
    -0.07
     farms
    -0.06
    Mono
    -0.06
    _fu
    -0.06
    _car
    -0.06
     propagated
    -0.06
    Blur
    -0.06
     دوره
    -0.06
    POSITIVE LOGITS
    TextWriter
    0.07
    employment
    0.07
    smith
    0.06
    สำเร
    0.06
    (age
    0.06
     sluts
    0.06
     scholarly
    0.06
     getId
    0.06
     задов
    0.05
     successor
    0.05
    Act Density 0.101%

    No Known Activations