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
     Raleigh
    -0.08
    .DESC
    -0.07
     dint
    -0.07
     hockey
    -0.07
    scrollTop
    -0.07
     Aussie
    -0.07
     Hockey
    -0.06
    ным
    -0.06
    도의
    -0.06
    Cli
    -0.06
    POSITIVE LOGITS
     waypoints
    0.07
    ��
    0.06
     **↵
    0.06
    **/↵
    0.06
    ordes
    0.06
    perienced
    0.06
     Verfüg
    0.06
    ('/')[-
    0.06
     expenditure
    0.06
     الموقع
    0.06
    Act Density 0.000%

    No Known Activations