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

    Neuronpedia

    INDEX
    Explanations

    physiological needs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ত্যার
    0.48
     Planning
    0.46
    IZATION
    0.45
     Games
    0.43
    AMPLES
    0.42
     OpenGL
    0.42
     Beverages
    0.42
     Recording
    0.42
    ্রাস
    0.42
     ![
    0.41
    POSITIVE LOGITS
    fuse
    0.47
     rivals
    0.45
    zione
    0.42
     exceptionally
    0.42
     stars
    0.40
    ковы
    0.40
     тот
    0.40
     যেটি
    0.40
    ッシュ
    0.39
     سيد
    0.39
    Act Density 0.000%

    No Known Activations