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

    Neuronpedia

    INDEX
    Explanations

    punctuation and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Notably
    1.18
    Alongside
    1.17
     overarching
    1.16
     nuanced
    1.15
    챱
    1.15
     underwhelming
    1.13
     badass
    1.09
     unsurprisingly
    1.07
     Notably
    1.05
     reimag
    1.00
    POSITIVE LOGITS
     grandchildren
    0.98
     muß
    0.98
       
    0.90
     lighted
    0.89
     handicapped
    0.89
     नही
    0.88
     granddaughter
    0.86
     ,
    0.85
     grandsons
    0.82
     granddaughters
    0.82
    Act Density 0.148%

    No Known Activations