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

    Neuronpedia

    INDEX
    Explanations

    let's do or plan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     อาจ
    0.88
     interstices
    0.83
    примеча
    0.80
     erforder
    0.76
     이후
    0.75
     присутствует
    0.74
    더라도
    0.72
     עצ
    0.71
     elaboration
    0.70
     explic
    0.69
    POSITIVE LOGITS
     unlock
    1.64
     unleash
    1.54
     harness
    1.50
     dive
    1.32
     Unlock
    1.32
     conquer
    1.30
    Unlock
    1.29
    unlock
    1.27
     unlocking
    1.27
     Unle
    1.27
    Act Density 1.813%

    No Known Activations