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

    Neuronpedia

    INDEX
    Explanations

    offering better

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     entertained
    0.46
    firebase
    0.44
    火
    0.43
     favorably
    0.42
    гре
    0.42
     घेतली
    0.42
    الية
    0.41
    abhave
    0.41
    жа
    0.41
     recruited
    0.41
    POSITIVE LOGITS
     Delf
    0.49
     bakers
    0.48
     Gamma
    0.46
    ↵
    0.46
     पैमाने
    0.46
     madd
    0.45
     ATF
    0.45
         
    0.45
     Haynes
    0.45
     Dickson
    0.45
    Act Density 0.006%

    No Known Activations