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

    Neuronpedia

    INDEX
    Explanations

    C++ template typename

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     orbitals
    1.33
     Cyber
    1.26
     Of
    1.25
     Draws
    1.21
     Concrete
    1.20
     Workshops
    1.19
     assumes
    1.19
    匯
    1.16
     Signature
    1.15
     Imports
    1.14
    POSITIVE LOGITS
    ers
    1.00
    un
    0.96
     size
    0.91
    ada
    0.88
    ab
    0.87
    u
    0.86
    uer
    0.83
    sp
    0.82
    size
    0.81
    ue
    0.81
    Act Density 0.000%

    No Known Activations