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

    Neuronpedia

    INDEX
    Explanations

    STEM fields and teachers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resourceful
    0.40
     didactic
    0.39
    ออกมา
    0.38
    sustainable
    0.37
    جواب
    0.37
     sustainable
    0.36
     വരു
    0.36
    هرات
    0.36
    源码
    0.36
     অভিভাবকদের
    0.35
    POSITIVE LOGITS
     शीर्ष
    0.50
     Experts
    0.49
    Experts
    0.44
     experts
    0.40
     Specialists
    0.40
     верх
    0.39
     Enhancement
    0.39
    plete
    0.38
     Anything
    0.38
    らった
    0.37
    Act Density 0.000%

    No Known Activations