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

    Neuronpedia

    INDEX
    Explanations

    likely reactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cabs
    0.45
     Albright
    0.45
     intrigued
    0.44
    Trains
    0.44
    வர்களாக
    0.44
    disconnect
    0.43
     with
    0.43
    ুখে
    0.43
     intrigue
    0.43
     poolside
    0.42
    POSITIVE LOGITS
    荣誉
    0.43
    länder
    0.42
    namen
    0.42
     folded
    0.41
    ismod
    0.39
    地區
    0.39
    凤
    0.38
    sov
    0.38
     список
    0.38
    崑
    0.38
    Act Density 0.005%

    No Known Activations