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

    Neuronpedia

    INDEX
    Explanations

    code/equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inputData
    -0.06
     ();↵↵
    -0.06
    нє
    -0.06
     сейчас
    -0.06
    sek
    -0.06
    /her
    -0.06
    かり
    -0.06
    )"
    -0.06
    없이
    -0.06
    /")↵
    -0.06
    POSITIVE LOGITS
    اید
    0.07
    集
    0.06
     estamos
    0.06
    uciones
    0.06
     blood
    0.06
    итуа
    0.06
     disproportion
    0.06
    >#
    0.06
    CLUDED
    0.06
    acellular
    0.06
    Act Density 0.001%

    No Known Activations