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

    Neuronpedia

    INDEX
    Explanations

    code context for entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     creditors
    0.50
     saints
    0.50
     angels
    0.47
     upas
    0.45
     religieux
    0.45
     meest
    0.44
     hoofd
    0.43
     serp
    0.42
     alertas
    0.42
     restorations
    0.42
    POSITIVE LOGITS
    integral
    0.49
    。
    0.49
    
    0.48
    ol
    0.46
    qa
    0.46
    intégr
    0.46
    )。
    0.45
    the
    0.45
    c
    0.45
    ir
    0.44
    Act Density 0.000%

    No Known Activations