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

    Neuronpedia

    INDEX
    Explanations

    problem-solving prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    唑
    0.72
     isTestSource
    0.72
    prue
    0.70
    rograman
    0.68
     \,\
    0.66
    洗
    0.66
     बेंगलुरु
    0.65
     aggior
    0.63
     కార్యక్రమంలో
    0.63
     egiten
    0.62
    POSITIVE LOGITS
     prompts
    1.21
     worksheet
    1.18
     handout
    1.09
     prompt
    1.08
     Worksheet
    1.07
     rubric
    1.07
     Prompt
    1.06
     pairs
    1.04
     ACTIVITY
    1.03
     assigned
    1.03
    Act Density 0.279%

    No Known Activations