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

    Neuronpedia

    INDEX
    Explanations

    district

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Coke
    -0.06
    พร
    -0.06
     سفید
    -0.06
     AJ
    -0.06
     coke
    -0.06
     playground
    -0.05
     mænd
    -0.05
     SCM
    -0.05
     lj
    -0.05
     relic
    -0.05
    POSITIVE LOGITS
    rust
    0.07
    输出
    0.07
     Blacks
    0.07
     ارزش
    0.07
    .so
    0.06
    clid
    0.06
     axial
    0.06
                    
    0.06
     arrivals
    0.06
    room
    0.06
    Act Density 0.003%

    No Known Activations