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

    Neuronpedia

    INDEX
    Explanations

    decided to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     décisions
    0.55
     made
    0.55
    made
    0.55
     decisions
    0.53
     Decision
    0.48
     decision
    0.47
    MADE
    0.46
    Made
    0.46
     MADE
    0.45
    ు
    0.45
    POSITIVE LOGITS
     upon
    0.59
     Upon
    0.58
    Upon
    0.50
    upon
    0.47
     productividad
    0.39
    configure
    0.38
    AndroidManifest
    0.37
     explorar
    0.37
     che
    0.37
     Productivity
    0.37
    Act Density 0.002%

    No Known Activations