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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    าศ
    -0.08
     と
    -0.07
    ाप
    -0.06
    уг
    -0.06
    ags
    -0.06
     flashy
    -0.06
    dux
    -0.06
     aj
    -0.06
    قع
    -0.06
    nton
    -0.06
    POSITIVE LOGITS
     }
↵
↵
    0.08
    firstName
    0.07
     лак
    0.07
    ethereum
    0.06
     našeho
    0.06
     第三
    0.06
    >↵↵↵
    0.06
     Spurs
    0.06
    lastName
    0.06
     //----------------
    0.06
    Act Density 0.001%

    No Known Activations