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

    Neuronpedia

    INDEX
    Explanations

    Python code contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    coordinated
    0.72
     obedient
    0.69
    skilled
    0.67
     गरेका
    0.66
     heredity
    0.66
    crew
    0.65
     haphazard
    0.64
     curved
    0.64
     chinos
    0.62
     conducive
    0.62
    POSITIVE LOGITS
     你
    0.93
     mağ
    0.87
    перь
    0.87
    首先
    0.86
     Falconer
    0.85
    经常
    0.84
    如果你
    0.84
     RPG
    0.83
     首先
    0.83
     Öncelikle
    0.82
    Act Density 0.000%

    No Known Activations