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

    Neuronpedia

    INDEX
    Explanations

    when followed by a clause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Җ
    0.47
     Oper
    0.43
     লইয়া
    0.43
    眈
    0.41
    cn
    0.41
    炜
    0.40
    abit
    0.40
    హ
    0.40
     हूँ
    0.40
    eous
    0.40
    POSITIVE LOGITS
     supplement
    0.39
     supplemental
    0.38
    supplement
    0.38
     stipulates
    0.36
     graders
    0.35
    부는
    0.35
     previewBuilder
    0.35
    ুরে
    0.35
     crossroads
    0.35
    plement
    0.35
    Act Density 0.000%

    No Known Activations