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

    Neuronpedia

    INDEX
    Explanations

    help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     one
    0.94
    ,
    0.93
     my
    0.92
     the
    0.89
    ie
    0.89
    пре
    0.86
     retailer
    0.84
    ר
    0.84
     slicing
    0.82
     F
    0.80
    POSITIVE LOGITS
     chegando
    1.10
    岖
    1.10
    پيديا
    1.05
     masyarakat
    1.03
     réfl
    1.03
     geomét
    1.02
     logotipo
    1.01
     Außerdem
    1.00
    트워크
    1.00
    一带
    1.00
    Act Density 0.022%

    No Known Activations