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

    Neuronpedia

    INDEX
    Explanations

    function prototypes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ko
    0.39
    aad
    0.39
    hog
    0.38
     受
    0.38
     backing
    0.37
    DataObject
    0.37
     Dickinson
    0.37
    祝
    0.37
     inf
    0.36
     booting
    0.36
    POSITIVE LOGITS
     prototypes
    0.60
     forward
    0.60
     Forward
    0.59
     prototype
    0.57
    Forward
    0.56
    forward
    0.55
    prototype
    0.53
     Prototype
    0.50
    Prototype
    0.47
     Prot
    0.47
    Act Density 0.018%

    No Known Activations