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

    Neuronpedia

    INDEX
    Explanations

    full names and production servers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     engel
    0.50
     Eng
    0.45
     Had
    0.41
     mél
    0.40
     GridSearchCV
    0.40
     Dynkin
    0.39
     Brings
    0.39
     രോഗ
    0.39
     Gm
    0.39
     bijvoorbeeld
    0.39
    POSITIVE LOGITS
    Detail
    0.56
    Message
    0.45
    Advance
    0.45
    Destination
    0.42
    बली
    0.42
    Map
    0.42
    Action
    0.42
     homage
    0.41
    itude
    0.41
    Area
    0.41
    Act Density 0.061%

    No Known Activations