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

    Neuronpedia

    INDEX
    Explanations

    Describing marches

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -owned
    -0.08
     thems
    -0.07
     tạp
    -0.07
    ár
    -0.06
    Sizes
    -0.06
     Cres
    -0.06
    折
    -0.06
     Poetry
    -0.06
    �
    -0.06
    prising
    -0.06
    POSITIVE LOGITS
     Diabetes
    0.07
     endwhile
    0.07
    :null
    0.07
    .ERR
    0.07
    =https
    0.06
     binnen
    0.06
    _DELETED
    0.06
     ayak
    0.06
     communicates
    0.06
    協
    0.06
    Act Density 0.005%

    No Known Activations