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

    Neuronpedia

    INDEX
    Explanations

    certainty questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    䈉
    0.41
    IFT
    0.38
    τρα
    0.38
    大胆
    0.38
    物を
    0.37
    ποίη
    0.37
    िफ्ट
    0.37
    ্ম্ম
    0.37
    atsu
    0.36
    лят
    0.36
    POSITIVE LOGITS
     familiarity
    0.45
     applicability
    0.44
     difficulties
    0.42
     walkways
    0.42
     walkway
    0.42
     origins
    0.42
     simplest
    0.41
     alap
    0.41
     challenges
    0.41
     strategies
    0.41
    Act Density 0.000%

    No Known Activations