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

    Neuronpedia

    INDEX
    Explanations

    user queries with specific instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ક્
    0.56
    防控
    0.53
     ಪು
    0.52
     ပြော
    0.50
    ácie
    0.49
     wijn
    0.49
    榞
    0.49
     добра
    0.48
     estudar
    0.48
    ordelen
    0.48
    POSITIVE LOGITS
    ir
    0.58
    ע
    0.47
     niche
    0.45
    Accounting
    0.45
     exposure
    0.44
     fetching
    0.44
    No
    0.43
     entities
    0.43
     expose
    0.43
    1
    0.43
    Act Density 0.000%

    No Known Activations