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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rozvoj
    -0.06
     Ree
    -0.06
    '_
    -0.06
     refreshing
    -0.06
     Reload
    -0.06
    .MapFrom
    -0.06
    окс
    -0.06
    صر
    -0.06
     Dump
    -0.06
     Fetch
    -0.06
    POSITIVE LOGITS
    Overflow
    0.07
    &&!
    0.06
    _imm
    0.06
    IRST
    0.06
    男
    0.06
    宙
    0.06
     garant
    0.06
    056
    0.06
    instanc
    0.06
     asynchronously
    0.06
    Act Density 0.003%

    No Known Activations