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

    Neuronpedia

    INDEX
    Explanations

    explanation structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     logos
    0.43
    罚
    0.40
    Home
    0.38
     competitors
    0.38
     messenger
    0.38
    Waypoint
    0.38
    います
    0.37
    MARK
    0.37
    Per
    0.37
    fruit
    0.37
    POSITIVE LOGITS
     Issled
    0.40
     preced
    0.38
     त्यानंतर
    0.38
     независимо
    0.38
    টিয়ে
    0.38
     অফ
    0.37
    ouvoir
    0.37
     unterschiedlich
    0.37
     музы
    0.36
     unatt
    0.36
    Act Density 0.000%

    No Known Activations