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

    Neuronpedia

    INDEX
    Explanations

    bummed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    assade
    0.74
     Cheese
    0.72
     প্রতী
    0.71
    <unused320>
    0.71
    Cheese
    0.69
    Dairy
    0.65
    陛
    0.65
    აცი
    0.65
    ACK
    0.65
    Frame
    0.64
    POSITIVE LOGITS
    ProxyAgent
    0.72
     tuple
    0.71
     chat
    0.70
     pyt
    0.69
     gene
    0.68
     Phelps
    0.68
     cope
    0.67
     role
    0.67
     IP
    0.67
     sympy
    0.66
    Act Density 0.010%

    No Known Activations