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

    Neuronpedia

    INDEX
    Explanations

    ?

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OPY
    -0.06
    کر
    -0.06
    ㅠㅠ
    -0.06
     arrog
    -0.06
     />,↵
    -0.06
     	↵
    -0.06
     Kut
    -0.06
     usern
    -0.06
     спроб
    -0.06
     عبد
    -0.06
    POSITIVE LOGITS
     chu
    0.07
    icipant
    0.06
    ुच
    0.06
    /job
    0.06
     CharSequence
    0.06
    /test
    0.06
     agon
    0.06
    cliffe
    0.06
     تت
    0.06
     onto
    0.06
    Act Density 0.000%

    No Known Activations