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

    Neuronpedia

    INDEX
    Explanations

    configuration or describes conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    াগ
    0.49
    ാത്ത
    0.48
    as
    0.47
    Agreement
    0.47
    హ
    0.46
    la
    0.45
    wym
    0.45
    нии
    0.44
    romad
    0.44
    ের
    0.44
    POSITIVE LOGITS
     ތ
    0.52
    SearchView
    0.48
     دیتے
    0.47
     FEMA
    0.45
     adsor
    0.45
    ,/
    0.45
     algal
    0.44
     AR
    0.44
     Sergeant
    0.43
     تھی۔
    0.43
    Act Density 0.000%

    No Known Activations