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

    Neuronpedia

    INDEX
    Explanations

    what questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    具体
    0.80
     pasti
    0.74
     chắc
    0.71
     Doodle
    0.70
    instance
    0.70
    Specific
    0.69
    یف
    0.69
    Specifically
    0.69
    Holding
    0.68
    UUID
    0.68
    POSITIVE LOGITS
     partition
    0.73
    '=>$
    0.72
     inequalities
    0.70
     mga
    0.68
    鋲
    0.68
     principles
    0.67
     unstructured
    0.67
     analyzers
    0.66
    までの
    0.65
     उतने
    0.64
    Act Density 0.055%

    No Known Activations