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

    Neuronpedia

    INDEX
    Explanations

    proposing and presenting ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Achievements
    0.82
     माहिती
    0.77
     Aprove
    0.77
     sağlar
    0.76
     hasilnya
    0.74
     Achievement
    0.73
     Directory
    0.72
     Rated
    0.71
     નિર્ણ
    0.71
    ര്‍ണ
    0.70
    POSITIVE LOGITS
     proposed
    1.96
     proposing
    1.81
     proposes
    1.75
     propose
    1.70
    proposed
    1.68
     articulated
    1.60
     выдви
    1.60
     Proposed
    1.58
     proffered
    1.57
     presented
    1.55
    Act Density 0.782%

    No Known Activations