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

    Neuronpedia

    INDEX
    Explanations

    gs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ولد
    -0.06
    **/↵↵
    -0.06
     شرق
    -0.06
     Hag
    -0.06
     Cần
    -0.06
    .dark
    -0.06
     Fak
    -0.06
    尤
    -0.06
    ได
    -0.06
     Vietnam
    -0.06
    POSITIVE LOGITS
    BIN
    0.07
     GS
    0.07
    dis
    0.07
    SP
    0.06
     
    0.06
    ersive
    0.06
     smoothing
    0.06
    VT
    0.06
    teş
    0.06
     ABS
    0.06
    Act Density 0.014%

    No Known Activations