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

    Neuronpedia

    INDEX
    Explanations

    acronyms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝐚
    0.88
    𝐨
    0.77
    atı
    0.68
    drinks
    0.67
    𝐮
    0.67
    uddin
    0.66
    ross
    0.65
    at
    0.65
    ri
    0.65
    𝐫
    0.63
    POSITIVE LOGITS
     Cerc
    0.95
     HPC
    0.94
     JC
    0.93
    crc
    0.92
    csc
    0.90
    crs
    0.90
     TIC
    0.89
     kpc
    0.89
     CRT
    0.89
    SCPC
    0.88
    Act Density 0.000%

    No Known Activations