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

    Neuronpedia

    INDEX
    Explanations

    ethical, idle, and content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ید
    1.43
     불구하고
    1.36
    ️⃣
    1.33
     kaynağından
    1.33
    ResourceType
    1.32
    ப்
    1.32
     zap
    1.30
    ″
    1.30
    ive
    1.28
    تی
    1.28
    POSITIVE LOGITS
    情况
    1.71
     χώ
    1.62
     hulk
    1.58
    ்ப
    1.58
     gew
    1.58
    近日
    1.57
    manship
    1.54
    peptide
    1.50
    PACE
    1.50
    ricks
    1.49
    Act Density 0.000%

    No Known Activations