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

    Neuronpedia

    INDEX
    Explanations

    concepts of reality and existence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cooperation
    0.46
    вяза
    0.44
     cooperación
    0.43
     collaboration
    0.43
     hb
    0.40
     cooperate
    0.39
    මාණ
    0.39
     сотрудни
    0.38
    გილ
    0.38
     হইতেছিল
    0.38
    POSITIVE LOGITS
    ?’”
    0.45
    चल
    0.43
    iyy
    0.39
    ٹس
    0.39
    ?[
    0.38
    ൫
    0.38
    ကြောင့်
    0.37
    ₁)
    0.37
    ƾ
    0.37
    inom
    0.37
    Act Density 0.000%

    No Known Activations