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
     sequentially
    -0.07
    -fluid
    -0.07
     deleting
    -0.06
    ergency
    -0.06
     delete
    -0.06
    IS
    -0.06
    	control
    -0.06
     controls
    -0.06
     convers
    -0.06
    opped
    -0.06
    POSITIVE LOGITS
     زیبا
    0.07
    .defaultValue
    0.06
     huyện
    0.06
    ěř
    0.06
     cadastr
    0.06
     звичай
    0.06
     Byl
    0.06
     straně
    0.06
    죠
    0.06
    �
    0.06
    Act Density 0.066%

    No Known Activations