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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dup
    -0.08
    /app
    -0.07
    采用
    -0.06
     kep
    -0.06
    沈
    -0.06
    Try
    -0.06
    散
    -0.06
    setw
    -0.06
     ры
    -0.06
     друга
    -0.06
    POSITIVE LOGITS
    ?”
    0.07
    gorit
    0.06
    ？”
    0.06
    ?’
    0.06
     Slovenia
    0.06
    ağın
    0.06
     сайте
    0.06
    атем
    0.06
     widths
    0.06
     realidad
    0.06
    Act Density 0.005%

    No Known Activations