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

    Neuronpedia

    INDEX
    Explanations

    solving equations by subtracting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vitt
    0.43
    searchResults
    0.43
     saison
    0.43
     türk
    0.42
     victorias
    0.41
    ğlu
    0.41
     preços
    0.41
     victoria
    0.41
    vykor
    0.40
    computation
    0.40
    POSITIVE LOGITS
     rewrite
    0.67
     steps
    0.64
     Steps
    0.62
     Rewrite
    0.62
    Rewrite
    0.62
     isolating
    0.61
    rewrite
    0.60
    Step
    0.60
    steps
    0.59
     rewriting
    0.59
    Act Density 0.028%

    No Known Activations