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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     evolved
    -0.07
    lings
    -0.07
    але
    -0.07
    (components
    -0.07
    Bit
    -0.07
    iris
    -0.06
     fancy
    -0.06
    expo
    -0.06
    _iter
    -0.06
     forced
    -0.06
    POSITIVE LOGITS
    ?>><?
    0.07
    ‌دهد
    0.06
     jul
    0.06
     unrealistic
    0.06
    .colorbar
    0.06
    (Cl
    0.06
    症
    0.06
     <*
    0.06
     تقس
    0.06
    #End
    0.06
    Act Density 0.063%

    No Known Activations