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

    Neuronpedia

    INDEX
    Explanations

    explanation and context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chef
    0.62
     Me
    0.53
     Re
    0.53
     Spell
    0.52
     total
    0.52
     sub
    0.51
     maximum
    0.51
     operations
    0.51
     brothers
    0.50
     Operation
    0.50
    POSITIVE LOGITS
    걷
    0.52
    Virtualized
    0.48
    нья
    0.47
     खिल
    0.47
    Implement
    0.46
    ꔹ
    0.45
    风景
    0.45
    前景
    0.45
    явления
    0.44
    CONTEXT
    0.44
    Act Density 0.001%

    No Known Activations