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

    Neuronpedia

    INDEX
    Explanations

    cucumber soup, speed, preserve, start values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BackendAuth
    0.46
     rhombus
    0.45
    RowNum
    0.45
    Founder
    0.44
    Rourke
    0.43
    PreferenceKey
    0.43
    Buyer
    0.42
     roky
    0.42
    backpack
    0.42
    לו
    0.41
    POSITIVE LOGITS
     autonome
    0.46
    essels
    0.46
     assemblages
    0.46
     intermediates
    0.46
     et
    0.45
     shaders
    0.45
     Intermediate
    0.45
     sucrose
    0.45
     Slate
    0.45
     chakra
    0.44
    Act Density 0.003%

    No Known Activations