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

    Neuronpedia

    INDEX
    Explanations

    tied

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    3
    0.54
    การ
    0.51
    di
    0.50
    du
    0.47
     cenu
    0.46
    g
    0.45
    gu
    0.45
    4
    0.44
    6
    0.44
    dt
    0.43
    POSITIVE LOGITS
    ෲ
    0.47
     Comanche
    0.46
     puzzling
    0.45
    MVCProject
    0.45
     pamphlets
    0.45
     expands
    0.44
     //#
    0.44
     transmits
    0.44
     aptly
    0.44
     improb
    0.44
    Act Density 0.000%

    No Known Activations