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

    Neuronpedia

    INDEX
    Explanations

    i am/was/understand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hopes
    0.85
     donna
    0.84
     glad
    0.81
     hope
    0.78
     unable
    0.77
     recommending
    0.76
     purposely
    0.76
     joke
    0.76
     obligé
    0.75
    ⣿
    0.75
    POSITIVE LOGITS
    Effective
    0.88
    Flexible
    0.85
     flexible
    0.83
    flexible
    0.80
    "?:
    0.75
     Czy
    0.72
    どのような
    0.71
     effective
    0.71
    テンツ
    0.70
     ගැනීම
    0.70
    Act Density 0.084%

    No Known Activations