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

    Neuronpedia

    INDEX
    Explanations

    debt, AI, or travel burdens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nop
    0.42
     cohes
    0.41
     cond
    0.41
     optimizations
    0.39
     ping
    0.39
     optimized
    0.39
     </>
    0.37
     ID
    0.37
    域
    0.37
     domain
    0.37
    POSITIVE LOGITS
     lovely
    0.47
    Lovely
    0.47
     наве
    0.46
    ibular
    0.45
     Lovely
    0.44
    lovely
    0.43
    burger
    0.42
     наві
    0.41
    lycer
    0.40
    너무
    0.40
    Act Density 0.000%

    No Known Activations