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

    Neuronpedia

    INDEX
    Explanations

    list formatting and direct explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    िकारक
    0.47
    㚼
    0.46
    organization
    0.43
    叱
    0.43
    sunami
    0.43
    cyt
    0.43
    workouts
    0.43
    ೇಯ
    0.43
    cations
    0.42
    koi
    0.42
    POSITIVE LOGITS
     troubled
    0.53
     Q
    0.47
     integer
    0.46
     fractured
    0.46
     sauf
    0.46
     mais
    0.46
     side
    0.45
     mont
    0.45
     unmanned
    0.45
     bigli
    0.45
    Act Density 0.001%

    No Known Activations