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

    Neuronpedia

    INDEX
    Explanations

    liquid surfaces, heat, water

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cud
    0.68
     kettle
    0.67
    मेट्री
    0.67
     Kettle
    0.62
    Sophie
    0.62
     Boy
    0.62
    বন্ধু
    0.62
    Statements
    0.61
    FBSDK
    0.61
    Keller
    0.61
    POSITIVE LOGITS
    ses
    0.74
    essels
    0.66
    PIO
    0.66
    Moles
    0.65
     atoms
    0.64
     bearing
    0.64
    ipro
    0.63
     dispose
    0.63
    UISE
    0.63
    ITAS
    0.61
    Act Density 0.014%

    No Known Activations