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

    Neuronpedia

    INDEX
    Explanations

    career advancement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     emulator
    0.85
    enegro
    0.82
     বিপক্ষে
    0.79
    ᓵ
    0.79
     goodness
    0.78
    sulfanyl
    0.77
    ainder
    0.77
    quisites
    0.77
     exclamation
    0.76
     προ
    0.76
    POSITIVE LOGITS
    ما
    0.75
    রা
    0.70
    П
    0.69
    цы
    0.69
    rid
    0.67
    務
    0.64
    ро
    0.64
    waitFor
    0.63
    ج
    0.63
    И
    0.63
    Act Density 0.101%

    No Known Activations