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

    Neuronpedia

    INDEX
    Explanations

    parentheses, code blocks, numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    सेन
    0.39
    ើន
    0.36
     RESON
    0.36
    ASGI
    0.36
    ὠ
    0.36
    िन
    0.35
    煅
    0.35
     नही
    0.35
    স্থার
    0.35
    句话
    0.35
    POSITIVE LOGITS
     checklists
    0.45
     gu
    0.36
     இல்ல
    0.35
     berbasis
    0.34
     tur
    0.34
     Steering
    0.34
     cho
    0.33
     bl
    0.33
     zero
    0.32
     اسٹ
    0.32
    Act Density 0.001%

    No Known Activations