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

    Neuronpedia

    INDEX
    Explanations

    ability to perform actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.41
    ,
    0.34
    '
    0.33
    -
    0.33
    1
    0.33
    6
    0.33
     The
    0.32
    :
    0.32
     (
    0.32
    ю
    0.32
    POSITIVE LOGITS
     integrate
    0.37
     facilement
    0.37
    ळं
    0.37
    ptăm
    0.36
     arrêt
    0.36
     configure
    0.36
     таком
    0.35
     bruke
    0.35
    ꞎ
    0.35
     använda
    0.35
    Act Density 0.002%

    No Known Activations