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

    Neuronpedia

    INDEX
    Explanations

    simple, cycle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SZ
    1.25
     PZ
    1.19
     MRS
    1.17
     Präsident
    1.14
     SZ
    1.13
     President
    1.12
     Eze
    1.12
    mz
    1.12
    Telex
    1.11
    汪
    1.09
    POSITIVE LOGITS
     Cycle
    1.71
    cycle
    1.67
     cycle
    1.64
    Cycle
    1.60
    サイクル
    1.57
     Cycles
    1.51
     cycles
    1.50
    cycles
    1.46
     cycling
    1.44
     Cycling
    1.43
    Act Density 2.997%

    No Known Activations