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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     poorest
    -0.06
    耐
    -0.06
    固
    -0.06
    íc
    -0.06
    -0.06
    Israeli
    -0.06
     треба
    -0.06
     igual
    -0.06
     builds
    -0.06
    .selected
    -0.06
    POSITIVE LOGITS
     quick
    0.07
    ../
    0.06
    plaintext
    0.06
    /Delete
    0.06
     expr
    0.06
    ласти
    0.06
    organ
    0.06
    	Application
    0.06
    $filter
    0.06
    .zip
    0.06
    Act Density 0.000%

    No Known Activations