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

    Neuronpedia

    INDEX
    Explanations

    feature or characteristic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     qty
    0.42
     fancy
    0.41
    |(
    0.40
     fanc
    0.40
    hander
    0.40
     hars
    0.39
     eventi
    0.39
     መጠን
    0.39
    ക്കുറ
    0.39
     skilful
    0.38
    POSITIVE LOGITS
    EN
    0.48
    AL
    0.46
    Okay
    0.46
    РУ
    0.45
     ویژگی
    0.44
    Feature
    0.43
    PRO
    0.42
    C
    0.40
    MOST
    0.39
    IN
    0.38
    Act Density 0.001%

    No Known Activations